openai-agents 0.0.17__tar.gz → 0.0.19__tar.gz

{openai_agents-0.0.17 → openai_agents-0.0.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openai-agents
-Version: 0.0.17
+Version: 0.0.19
 Summary: OpenAI Agents SDK
 Project-URL: Homepage, https://github.com/openai/openai-agents-python
 Project-URL: Repository, https://github.com/openai/openai-agents-python
@@ -19,8 +19,8 @@ Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Typing :: Typed
 Requires-Python: >=3.9
 Requires-Dist: griffe<2,>=1.5.6
-Requires-Dist: mcp<2,>=1.8.0; python_version >= '3.10'
-Requires-Dist: openai>=1.81.0
+Requires-Dist: mcp<2,>=1.9.4; python_version >= '3.10'
+Requires-Dist: openai>=1.87.0
 Requires-Dist: pydantic<3,>=2.10
 Requires-Dist: requests<3,>=2.0
 Requires-Dist: types-requests<3,>=2.0
@@ -40,6 +40,9 @@ The OpenAI Agents SDK is a lightweight yet powerful framework for building multi
 
 <img src="https://cdn.openai.com/API/docs/images/orchestration.png" alt="Image of the Agents Tracing UI" style="max-height: 803px;">
 
+> [!NOTE]
+> Looking for the JavaScript/TypeScript version? Check out [Agents SDK JS/TS](https://github.com/openai/openai-agents-js).
+
 ### Core concepts:
 
 1. [**Agents**](https://openai.github.io/openai-agents-python/agents): LLMs configured with instructions, tools, guardrails, and handoffs

{openai_agents-0.0.17 → openai_agents-0.0.19}/README.md

@@ -4,6 +4,9 @@ The OpenAI Agents SDK is a lightweight yet powerful framework for building multi
 
 <img src="https://cdn.openai.com/API/docs/images/orchestration.png" alt="Image of the Agents Tracing UI" style="max-height: 803px;">
 
+> [!NOTE]
+> Looking for the JavaScript/TypeScript version? Check out [Agents SDK JS/TS](https://github.com/openai/openai-agents-js).
+
 ### Core concepts:
 
 1. [**Agents**](https://openai.github.io/openai-agents-python/agents): LLMs configured with instructions, tools, guardrails, and handoffs

openai_agents-0.0.19/docs/ja/repl.md

@@ -0,0 +1,22 @@
+---
+search:
+  exclude: true
+---
+# REPL ユーティリティ
+
+`run_demo_loop` を使うと、ターミナルから手軽にエージェントを試せます。
+
+```python
+import asyncio
+from agents import Agent, run_demo_loop
+
+async def main() -> None:
+    agent = Agent(name="Assistant", instructions="あなたは親切なアシスタントです")
+    await run_demo_loop(agent)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+`run_demo_loop` は入力を繰り返し受け取り、会話履歴を保持したままエージェントを実行します。既定ではストリーミング出力を表示します。
+`quit` または `exit` と入力するか `Ctrl-D` を押すと終了します。

openai_agents-0.0.19/docs/ref/repl.md

@@ -0,0 +1,6 @@
+# `repl`
+
+::: agents.repl
+    options:
+        members:
+            - run_demo_loop

openai_agents-0.0.19/docs/release.md

@@ -0,0 +1,18 @@
+# Release process
+
+The project follows a slightly modified version of semantic versioning using the form `0.Y.Z`. The leading `0` indicates the SDK is still evolving rapidly. Increment the components as follows:
+
+## Minor (`Y`) versions
+
+We will increase minor versions `Y` for **breaking changes** to any public interfaces that are not marked as beta. For example, going from `0.0.x` to `0.1.x` might include breaking changes.
+
+If you don't want breaking changes, we recommend pinning to `0.0.x` versions in your project.
+
+## Patch (`Z`) versions
+
+We will increment `Z` for non-breaking changes:
+
+- Bug fixes
+- New features
+- Changes to private interfaces
+- Updates to beta features

openai_agents-0.0.19/docs/repl.md

@@ -0,0 +1,19 @@
+# REPL utility
+
+The SDK provides `run_demo_loop` for quick interactive testing.
+
+```python
+import asyncio
+from agents import Agent, run_demo_loop
+
+async def main() -> None:
+    agent = Agent(name="Assistant", instructions="You are a helpful assistant.")
+    await run_demo_loop(agent)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+`run_demo_loop` prompts for user input in a loop, keeping the conversation
+history between turns. By default it streams model output as it is produced.
+Type `quit` or `exit` (or press `Ctrl-D`) to leave the loop.

{openai_agents-0.0.17 → openai_agents-0.0.19}/docs/tools.md

@@ -284,6 +284,33 @@ async def run_my_agent() -> str:
     return str(result.final_output)
 ```
 
+### Custom output extraction
+
+In certain cases, you might want to modify the output of the tool-agents before returning it to the central agent. This may be useful if you want to:
+
+- Extract a specific piece of information (e.g., a JSON payload) from the sub-agent's chat history.
+- Convert or reformat the agent’s final answer (e.g., transform Markdown into plain text or CSV).
+- Validate the output or provide a fallback value when the agent’s response is missing or malformed.
+
+You can do this by supplying the `custom_output_extractor` argument to the `as_tool` method:
+
+```python
+async def extract_json_payload(run_result: RunResult) -> str:
+    # Scan the agent’s outputs in reverse order until we find a JSON-like message from a tool call.
+    for item in reversed(run_result.new_items):
+        if isinstance(item, ToolCallOutputItem) and item.output.strip().startswith("{"):
+            return item.output.strip()
+    # Fallback to an empty JSON object if nothing was found
+    return "{}"
+
+
+json_tool = data_agent.as_tool(
+    tool_name="get_data_json",
+    tool_description="Run the data agent and return only its JSON payload",
+    custom_output_extractor=extract_json_payload,
+)
+```
+
 ## Handling errors in function tools
 
 When you create a function tool via `@function_tool`, you can pass a `failure_error_function`. This is a function that provides an error response to the LLM in case the tool call crashes.

openai_agents-0.0.19/examples/basic/prompt_template.py

@@ -0,0 +1,79 @@
+import argparse
+import asyncio
+import random
+
+from agents import Agent, GenerateDynamicPromptData, Runner
+
+"""
+NOTE: This example will not work out of the box, because the default prompt ID will not be available
+in your project.
+
+To use it, please:
+1. Go to https://platform.openai.com/playground/prompts
+2. Create a new prompt variable, `poem_style`.
+3. Create a system prompt with the content:
+```
+Write a poem in {{poem_style}}
+```
+4. Run the example with the `--prompt-id` flag.
+"""
+
+DEFAULT_PROMPT_ID = "pmpt_6850729e8ba481939fd439e058c69ee004afaa19c520b78b"
+
+
+class DynamicContext:
+    def __init__(self, prompt_id: str):
+        self.prompt_id = prompt_id
+        self.poem_style = random.choice(["limerick", "haiku", "ballad"])
+        print(f"[debug] DynamicContext initialized with poem_style: {self.poem_style}")
+
+
+async def _get_dynamic_prompt(data: GenerateDynamicPromptData):
+    ctx: DynamicContext = data.context.context
+    return {
+        "id": ctx.prompt_id,
+        "version": "1",
+        "variables": {
+            "poem_style": ctx.poem_style,
+        },
+    }
+
+
+async def dynamic_prompt(prompt_id: str):
+    context = DynamicContext(prompt_id)
+
+    agent = Agent(
+        name="Assistant",
+        prompt=_get_dynamic_prompt,
+    )
+
+    result = await Runner.run(agent, "Tell me about recursion in programming.", context=context)
+    print(result.final_output)
+
+
+async def static_prompt(prompt_id: str):
+    agent = Agent(
+        name="Assistant",
+        prompt={
+            "id": prompt_id,
+            "version": "1",
+            "variables": {
+                "poem_style": "limerick",
+            },
+        },
+    )
+
+    result = await Runner.run(agent, "Tell me about recursion in programming.")
+    print(result.final_output)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--dynamic", action="store_true")
+    parser.add_argument("--prompt-id", type=str, default=DEFAULT_PROMPT_ID)
+    args = parser.parse_args()
+
+    if args.dynamic:
+        asyncio.run(dynamic_prompt(args.prompt_id))
+    else:
+        asyncio.run(static_prompt(args.prompt_id))

{openai_agents-0.0.17 → openai_agents-0.0.19}/mkdocs.yml

@@ -59,6 +59,7 @@ plugins:
                 - running_agents.md
                 - results.md
                 - streaming.md
+                - repl.md
                 - tools.md
                 - mcp.md
                 - handoffs.md
@@ -71,6 +72,7 @@ plugins:
                     - models/litellm.md
                 - config.md
                 - visualization.md
+                - release.md
                 - Voice agents:
                     - voice/quickstart.md
                     - voice/pipeline.md
@@ -80,6 +82,7 @@ plugins:
                     - ref/index.md
                     - ref/agent.md
                     - ref/run.md
+                    - ref/repl.md
                     - ref/tool.md
                     - ref/result.md
                     - ref/stream_events.md
@@ -139,6 +142,7 @@ plugins:
                 - running_agents.md
                 - results.md
                 - streaming.md
+                - repl.md
                 - tools.md
                 - mcp.md
                 - handoffs.md

{openai_agents-0.0.17 → openai_agents-0.0.19}/pyproject.toml

@@ -1,19 +1,19 @@
 [project]
 name = "openai-agents"
-version = "0.0.17"
+version = "0.0.19"
 description = "OpenAI Agents SDK"
 readme = "README.md"
 requires-python = ">=3.9"
 license = "MIT"
 authors = [{ name = "OpenAI", email = "support@openai.com" }]
 dependencies = [
-    "openai>=1.81.0",
+    "openai>=1.87.0",
     "pydantic>=2.10, <3",
     "griffe>=1.5.6, <2",
     "typing-extensions>=4.12.2, <5",
     "requests>=2.0, <3",
     "types-requests>=2.0, <3",
-    "mcp>=1.8.0, <2; python_version >= '3.10'",
+    "mcp>=1.9.4, <2; python_version >= '3.10'",
 ]
 classifiers = [
     "Typing :: Typed",

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/__init__.py

@@ -45,6 +45,8 @@ from .models.interface import Model, ModelProvider, ModelTracing
 from .models.openai_chatcompletions import OpenAIChatCompletionsModel
 from .models.openai_provider import OpenAIProvider
 from .models.openai_responses import OpenAIResponsesModel
+from .prompts import DynamicPromptFunction, GenerateDynamicPromptData, Prompt
+from .repl import run_demo_loop
 from .result import RunResult, RunResultStreaming
 from .run import RunConfig, Runner
 from .run_context import RunContextWrapper, TContext
@@ -102,6 +104,7 @@ from .tracing import (
     handoff_span,
     mcp_tools_span,
     set_trace_processors,
+    set_trace_provider,
     set_tracing_disabled,
     set_tracing_export_api_key,
     speech_group_span,
@@ -160,6 +163,7 @@ __all__ = [
     "ToolsToFinalOutputFunction",
     "ToolsToFinalOutputResult",
     "Runner",
+    "run_demo_loop",
     "Model",
     "ModelProvider",
     "ModelTracing",
@@ -176,6 +180,9 @@ __all__ = [
     "AgentsException",
     "InputGuardrailTripwireTriggered",
     "OutputGuardrailTripwireTriggered",
+    "DynamicPromptFunction",
+    "GenerateDynamicPromptData",
+    "Prompt",
     "MaxTurnsExceeded",
     "ModelBehaviorError",
     "UserError",
@@ -240,6 +247,7 @@ __all__ = [
     "guardrail_span",
     "handoff_span",
     "set_trace_processors",
+    "set_trace_provider",
     "set_tracing_disabled",
     "speech_group_span",
     "transcription_span",

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/_run_impl.py

@@ -75,6 +75,7 @@ from .tool import (
     MCPToolApprovalRequest,
     Tool,
 )
+from .tool_context import ToolContext
 from .tracing import (
     SpanError,
     Trace,
@@ -543,23 +544,24 @@ class RunImpl:
             func_tool: FunctionTool, tool_call: ResponseFunctionToolCall
         ) -> Any:
             with function_span(func_tool.name) as span_fn:
+                tool_context = ToolContext.from_agent_context(context_wrapper, tool_call.call_id)
                 if config.trace_include_sensitive_data:
                     span_fn.span_data.input = tool_call.arguments
                 try:
                     _, _, result = await asyncio.gather(
-                        hooks.on_tool_start(context_wrapper, agent, func_tool),
+                        hooks.on_tool_start(tool_context, agent, func_tool),
                         (
-                            agent.hooks.on_tool_start(context_wrapper, agent, func_tool)
+                            agent.hooks.on_tool_start(tool_context, agent, func_tool)
                             if agent.hooks
                             else _coro.noop_coroutine()
                         ),
-                        func_tool.on_invoke_tool(context_wrapper, tool_call.arguments),
+                        func_tool.on_invoke_tool(tool_context, tool_call.arguments),
                     )
 
                     await asyncio.gather(
-                        hooks.on_tool_end(context_wrapper, agent, func_tool, result),
+                        hooks.on_tool_end(tool_context, agent, func_tool, result),
                         (
-                            agent.hooks.on_tool_end(context_wrapper, agent, func_tool, result)
+                            agent.hooks.on_tool_end(tool_context, agent, func_tool, result)
                             if agent.hooks
                             else _coro.noop_coroutine()
                         ),

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/agent.py

@@ -7,6 +7,7 @@ from collections.abc import Awaitable
 from dataclasses import dataclass, field
 from typing import TYPE_CHECKING, Any, Callable, Generic, Literal, cast
 
+from openai.types.responses.response_prompt_param import ResponsePromptParam
 from typing_extensions import NotRequired, TypeAlias, TypedDict
 
 from .agent_output import AgentOutputSchemaBase
@@ -17,6 +18,7 @@ from .logger import logger
 from .mcp import MCPUtil
 from .model_settings import ModelSettings
 from .models.interface import Model
+from .prompts import DynamicPromptFunction, Prompt, PromptUtil
 from .run_context import RunContextWrapper, TContext
 from .tool import FunctionTool, FunctionToolResult, Tool, function_tool
 from .util import _transforms
@@ -95,6 +97,12 @@ class Agent(Generic[TContext]):
     return a string.
     """
 
+    prompt: Prompt | DynamicPromptFunction | None = None
+    """A prompt object (or a function that returns a Prompt). Prompts allow you to dynamically
+    configure the instructions, tools and other config for an agent outside of your code. Only
+    usable with OpenAI models, using the Responses API.
+    """
+
     handoff_description: str | None = None
     """A description of the agent. This is used when the agent is used as a handoff, so that an
     LLM knows what it does and when to invoke it.
@@ -242,6 +250,12 @@ class Agent(Generic[TContext]):
 
         return None
 
+    async def get_prompt(
+        self, run_context: RunContextWrapper[TContext]
+    ) -> ResponsePromptParam | None:
+        """Get the prompt for the agent."""
+        return await PromptUtil.to_model_input(self.prompt, run_context, self)
+
     async def get_mcp_tools(self) -> list[Tool]:
         """Fetches the available tools from the MCP servers."""
         convert_schemas_to_strict = self.mcp_config.get("convert_schemas_to_strict", False)

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/extensions/models/litellm_model.py

@@ -71,6 +71,7 @@ class LitellmModel(Model):
         handoffs: list[Handoff],
         tracing: ModelTracing,
         previous_response_id: str | None,
+        prompt: Any | None = None,
     ) -> ModelResponse:
         with generation_span(
             model=str(self.model),
@@ -88,6 +89,7 @@ class LitellmModel(Model):
                 span_generation,
                 tracing,
                 stream=False,
+                prompt=prompt,
             )
 
             assert isinstance(response.choices[0], litellm.types.utils.Choices)
@@ -153,8 +155,8 @@ class LitellmModel(Model):
         output_schema: AgentOutputSchemaBase | None,
         handoffs: list[Handoff],
         tracing: ModelTracing,
-        *,
         previous_response_id: str | None,
+        prompt: Any | None = None,
     ) -> AsyncIterator[TResponseStreamEvent]:
         with generation_span(
             model=str(self.model),
@@ -172,6 +174,7 @@ class LitellmModel(Model):
                 span_generation,
                 tracing,
                 stream=True,
+                prompt=prompt,
             )
 
             final_response: Response | None = None
@@ -202,6 +205,7 @@ class LitellmModel(Model):
         span: Span[GenerationSpanData],
         tracing: ModelTracing,
         stream: Literal[True],
+        prompt: Any | None = None,
     ) -> tuple[Response, AsyncStream[ChatCompletionChunk]]: ...
 
     @overload
@@ -216,6 +220,7 @@ class LitellmModel(Model):
         span: Span[GenerationSpanData],
         tracing: ModelTracing,
         stream: Literal[False],
+        prompt: Any | None = None,
     ) -> litellm.types.utils.ModelResponse: ...
 
     async def _fetch_response(
@@ -229,6 +234,7 @@ class LitellmModel(Model):
         span: Span[GenerationSpanData],
         tracing: ModelTracing,
         stream: bool = False,
+        prompt: Any | None = None,
     ) -> litellm.types.utils.ModelResponse | tuple[Response, AsyncStream[ChatCompletionChunk]]:
         converted_messages = Converter.items_to_messages(input)
 
@@ -284,6 +290,10 @@ class LitellmModel(Model):
         if model_settings.extra_body and isinstance(model_settings.extra_body, dict):
             extra_kwargs.update(model_settings.extra_body)
 
+        # Add kwargs from model_settings.extra_args, filtering out None values
+        if model_settings.extra_args:
+            extra_kwargs.update(model_settings.extra_args)
+
         ret = await litellm.acompletion(
             model=self.model,
             messages=converted_messages,

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/function_schema.py

@@ -13,6 +13,7 @@ from pydantic import BaseModel, Field, create_model
 from .exceptions import UserError
 from .run_context import RunContextWrapper
 from .strict_schema import ensure_strict_json_schema
+from .tool_context import ToolContext
 
 
 @dataclass
@@ -222,7 +223,8 @@ def function_schema(
         doc_info = None
         param_descs = {}
 
-    func_name = name_override or doc_info.name if doc_info else func.__name__
+    # Ensure name_override takes precedence even if docstring info is disabled.
+    func_name = name_override or (doc_info.name if doc_info else func.__name__)
 
     # 2. Inspect function signature and get type hints
     sig = inspect.signature(func)
@@ -237,21 +239,21 @@ def function_schema(
         ann = type_hints.get(first_name, first_param.annotation)
         if ann != inspect._empty:
             origin = get_origin(ann) or ann
-            if origin is RunContextWrapper:
+            if origin is RunContextWrapper or origin is ToolContext:
                 takes_context = True  # Mark that the function takes context
             else:
                 filtered_params.append((first_name, first_param))
         else:
             filtered_params.append((first_name, first_param))
 
-    # For parameters other than the first, raise error if any use RunContextWrapper.
+    # For parameters other than the first, raise error if any use RunContextWrapper or ToolContext.
     for name, param in params[1:]:
         ann = type_hints.get(name, param.annotation)
         if ann != inspect._empty:
             origin = get_origin(ann) or ann
-            if origin is RunContextWrapper:
+            if origin is RunContextWrapper or origin is ToolContext:
                 raise UserError(
-                    f"RunContextWrapper param found at non-first position in function"
+                    f"RunContextWrapper/ToolContext param found at non-first position in function"
                     f" {func.__name__}"
                 )
         filtered_params.append((name, param))

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/handoffs.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import inspect
+import json
 from collections.abc import Awaitable
 from dataclasses import dataclass
 from typing import TYPE_CHECKING, Any, Callable, Generic, cast, overload
@@ -99,8 +100,7 @@ class Handoff(Generic[TContext]):
     """
 
     def get_transfer_message(self, agent: Agent[Any]) -> str:
-        base = f"{{'assistant': '{agent.name}'}}"
-        return base
+        return json.dumps({"assistant": agent.name})
 
     @classmethod
     def default_tool_name(cls, agent: Agent[Any]) -> str:

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/mcp/server.py

@@ -340,10 +340,10 @@ class MCPServerStreamableHttpParams(TypedDict):
     headers: NotRequired[dict[str, str]]
     """The headers to send to the server."""
 
-    timeout: NotRequired[timedelta]
+    timeout: NotRequired[timedelta | float]
     """The timeout for the HTTP request. Defaults to 5 seconds."""
 
-    sse_read_timeout: NotRequired[timedelta]
+    sse_read_timeout: NotRequired[timedelta | float]
     """The timeout for the SSE connection, in seconds. Defaults to 5 minutes."""
 
     terminate_on_close: NotRequired[bool]
@@ -401,8 +401,8 @@ class MCPServerStreamableHttp(_MCPServerWithClientSession):
         return streamablehttp_client(
             url=self.params["url"],
             headers=self.params.get("headers", None),
-            timeout=self.params.get("timeout", timedelta(seconds=30)),
-            sse_read_timeout=self.params.get("sse_read_timeout", timedelta(seconds=60 * 5)),
+            timeout=self.params.get("timeout", 5),
+            sse_read_timeout=self.params.get("sse_read_timeout", 60 * 5),
             terminate_on_close=self.params.get("terminate_on_close", True),
         )
 

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/model_settings.py

@@ -73,6 +73,11 @@ class ModelSettings:
     """Additional headers to provide with the request.
     Defaults to None if not provided."""
 
+    extra_args: dict[str, Any] | None = None
+    """Arbitrary keyword arguments to pass to the model API call.
+    These will be passed directly to the underlying model provider's API.
+    Use with caution as not all models support all parameters."""
+
     def resolve(self, override: ModelSettings | None) -> ModelSettings:
         """Produce a new ModelSettings by overlaying any non-None values from the
         override on top of this instance."""
@@ -84,6 +89,16 @@ class ModelSettings:
             for field in fields(self)
             if getattr(override, field.name) is not None
         }
+
+        # Handle extra_args merging specially - merge dictionaries instead of replacing
+        if self.extra_args is not None or override.extra_args is not None:
+            merged_args = {}
+            if self.extra_args:
+                merged_args.update(self.extra_args)
+            if override.extra_args:
+                merged_args.update(override.extra_args)
+            changes["extra_args"] = merged_args if merged_args else None
+
         return replace(self, **changes)
 
     def to_json_dict(self) -> dict[str, Any]:

{openai_agents-0.0.17 → openai_agents-0.0.19}/src/agents/models/interface.py

@@ -5,6 +5,8 @@ import enum
 from collections.abc import AsyncIterator
 from typing import TYPE_CHECKING
 
+from openai.types.responses.response_prompt_param import ResponsePromptParam
+
 from ..agent_output import AgentOutputSchemaBase
 from ..handoffs import Handoff
 from ..items import ModelResponse, TResponseInputItem, TResponseStreamEvent
@@ -46,6 +48,7 @@ class Model(abc.ABC):
         tracing: ModelTracing,
         *,
         previous_response_id: str | None,
+        prompt: ResponsePromptParam | None,
     ) -> ModelResponse:
         """Get a response from the model.
 
@@ -59,6 +62,7 @@ class Model(abc.ABC):
             tracing: Tracing configuration.
             previous_response_id: the ID of the previous response. Generally not used by the model,
                 except for the OpenAI Responses API.
+            prompt: The prompt config to use for the model.
 
         Returns:
             The full model response.
@@ -77,6 +81,7 @@ class Model(abc.ABC):
         tracing: ModelTracing,
         *,
         previous_response_id: str | None,
+        prompt: ResponsePromptParam | None,
     ) -> AsyncIterator[TResponseStreamEvent]:
         """Stream a response from the model.
 
@@ -90,6 +95,7 @@ class Model(abc.ABC):
             tracing: Tracing configuration.
             previous_response_id: the ID of the previous response. Generally not used by the model,
                 except for the OpenAI Responses API.
+            prompt: The prompt config to use for the model.
 
         Returns:
             An iterator of response stream events, in OpenAI Responses format.