Update examples and defaults to GPT-5.5 (#3016)

Author: alfozan

docs/agents.md

@@ -301,7 +301,7 @@ By using the `clone()` method on an agent, you can duplicate an Agent, and optio
 pirate_agent = Agent(
     name="Pirate",
     instructions="Write like a pirate",
-    model="gpt-5.4",
+    model="gpt-5.5",
 )
 
 robot_agent = pirate_agent.clone(

docs/models/index.md

@@ -22,16 +22,16 @@ Start with the simplest path that fits your setup:
 
 For most OpenAI-only apps, the recommended path is to use string model names with the default OpenAI provider and stay on the Responses model path.
 
-When you don't specify a model when initializing an `Agent`, the default model will be used. The default is currently [`gpt-4.1`](https://developers.openai.com/api/docs/models/gpt-4.1) for compatibility and low latency. If you have access, we recommend setting your agents to [`gpt-5.4`](https://developers.openai.com/api/docs/models/gpt-5.4) for higher quality while keeping explicit `model_settings`.
+When you don't specify a model when initializing an `Agent`, the default model will be used. The default is currently [`gpt-4.1`](https://developers.openai.com/api/docs/models/gpt-4.1) for compatibility and low latency. If you have access, we recommend setting your agents to [`gpt-5.5`](https://developers.openai.com/api/docs/models/gpt-5.5) for higher quality while keeping explicit `model_settings`.
 
-If you want to switch to other models like [`gpt-5.4`](https://developers.openai.com/api/docs/models/gpt-5.4), there are two ways to configure your agents.
+If you want to switch to other models like [`gpt-5.5`](https://developers.openai.com/api/docs/models/gpt-5.5), there are two ways to configure your agents.
 
 ### Default model
 
 First, if you want to consistently use a specific model for all agents that do not set a custom model, set the `OPENAI_DEFAULT_MODEL` environment variable before running your agents.
 
 ```bash
-export OPENAI_DEFAULT_MODEL=gpt-5.4
+export OPENAI_DEFAULT_MODEL=gpt-5.5
 python3 my_awesome_agent.py
 ```
 
@@ -48,13 +48,13 @@ agent = Agent(
 result = await Runner.run(
     agent,
     "Hello",
-    run_config=RunConfig(model="gpt-5.4"),
+    run_config=RunConfig(model="gpt-5.5"),
 )
 ```
 
 #### GPT-5 models
 
-When you use any GPT-5 model such as [`gpt-5.4`](https://developers.openai.com/api/docs/models/gpt-5.4) in this way, the SDK applies default `ModelSettings`. It sets the ones that work the best for most use cases. To adjust the reasoning effort for the default model, pass your own `ModelSettings`:
+When you use any GPT-5 model such as [`gpt-5.5`](https://developers.openai.com/api/docs/models/gpt-5.5) in this way, the SDK applies default `ModelSettings`. It sets the ones that work the best for most use cases. To adjust the reasoning effort for the default model, pass your own `ModelSettings`:
 
 ```python
 from openai.types.shared import Reasoning
@@ -63,20 +63,20 @@ from agents import Agent, ModelSettings
 my_agent = Agent(
     name="My Agent",
     instructions="You're a helpful agent.",
-    # If OPENAI_DEFAULT_MODEL=gpt-5.4 is set, passing only model_settings works.
+    # If OPENAI_DEFAULT_MODEL=gpt-5.5 is set, passing only model_settings works.
     # It's also fine to pass a GPT-5 model name explicitly:
-    model="gpt-5.4",
+    model="gpt-5.5",
     model_settings=ModelSettings(reasoning=Reasoning(effort="high"), verbosity="low")
 )
 ```
 
-For lower latency, using `reasoning.effort="none"` with `gpt-5.4` is recommended. The gpt-4.1 family (including mini and nano variants) also remains a solid choice for building interactive agent apps.
+For lower latency, using `reasoning.effort="none"` with `gpt-5.5` is recommended. The gpt-4.1 family (including mini and nano variants) also remains a solid choice for building interactive agent apps.
 
 #### ComputerTool model selection
 
-If an agent includes [`ComputerTool`][agents.tool.ComputerTool], the effective model on the actual Responses request determines which computer-tool payload the SDK sends. Explicit `gpt-5.4` requests use the GA built-in `computer` tool, while explicit `computer-use-preview` requests keep the older `computer_use_preview` payload.
+If an agent includes [`ComputerTool`][agents.tool.ComputerTool], the effective model on the actual Responses request determines which computer-tool payload the SDK sends. Explicit `gpt-5.5` requests use the GA built-in `computer` tool, while explicit `computer-use-preview` requests keep the older `computer_use_preview` payload.
 
-Prompt-managed calls are the main exception. If a prompt template owns the model and the SDK omits `model` from the request, the SDK defaults to the preview-compatible computer payload so it does not guess which model the prompt pins. To keep the GA path in that flow, either make `model="gpt-5.4"` explicit on the request or force the GA selector with `ModelSettings(tool_choice="computer")` or `ModelSettings(tool_choice="computer_use")`.
+Prompt-managed calls are the main exception. If a prompt template owns the model and the SDK omits `model` from the request, the SDK defaults to the preview-compatible computer payload so it does not guess which model the prompt pins. To keep the GA path in that flow, either make `model="gpt-5.5"` explicit on the request or force the GA selector with `ModelSettings(tool_choice="computer")` or `ModelSettings(tool_choice="computer_use")`.
 
 With a registered [`ComputerTool`][agents.tool.ComputerTool], `tool_choice="computer"`, `"computer_use"`, and `"computer_use_preview"` are normalized to the built-in selector that matches the effective request model. If no `ComputerTool` is registered, those strings continue to behave like ordinary function names.
 
@@ -108,7 +108,7 @@ from agents import set_default_openai_responses_transport
 set_default_openai_responses_transport("websocket")
 ```
 
-This affects OpenAI Responses models resolved by the default OpenAI provider (including string model names such as `"gpt-5.4"`).
+This affects OpenAI Responses models resolved by the default OpenAI provider (including string model names such as `"gpt-5.5"`).
 
 Transport selection happens when the SDK resolves a model name into a model instance. If you pass a concrete [`Model`][agents.models.interface.Model] object, its transport is already fixed: [`OpenAIResponsesWSModel`][agents.models.openai_responses.OpenAIResponsesWSModel] uses websocket, [`OpenAIResponsesModel`][agents.models.openai_responses.OpenAIResponsesModel] uses HTTP, and [`OpenAIChatCompletionsModel`][agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] stays on Chat Completions. If you pass `RunConfig(model_provider=...)`, that provider controls transport selection instead of the global default.
 
@@ -275,7 +275,7 @@ triage_agent = Agent(
     name="Triage agent",
     instructions="Handoff to the appropriate agent based on the language of the request.",
     handoffs=[spanish_agent, english_agent],
-    model="gpt-5.4",
+    model="gpt-5.5",
 )
 
 async def main():
@@ -320,7 +320,7 @@ from agents import Agent, ModelSettings
 
 research_agent = Agent(
     name="Research agent",
-    model="gpt-5.4",
+    model="gpt-5.5",
     model_settings=ModelSettings(
         parallel_tool_calls=False,
         truncation="auto",
@@ -363,7 +363,7 @@ from agents import Agent, ModelRetrySettings, ModelSettings, retry_policies
 
 agent = Agent(
     name="Assistant",
-    model="gpt-5.4",
+    model="gpt-5.5",
     model_settings=ModelSettings(
         retry=ModelRetrySettings(
             max_retries=4,

docs/results.md

@@ -59,7 +59,7 @@ In practice:
 
 Unlike the JavaScript SDK, Python does not expose a separate `output` property for the model-shaped delta only. Use `new_items` when you need SDK metadata, or inspect `raw_responses` when you need the raw model payloads.
 
-Computer-tool replay follows the raw Responses payload shape. Preview-model `computer_call` items preserve a single `action`, while `gpt-5.4` computer calls can preserve batched `actions[]`. [`to_input_list()`][agents.result.RunResultBase.to_input_list] and [`RunState`][agents.run_state.RunState] keep whichever shape the model produced, so manual replay, pause/resume flows, and stored transcripts continue to work across both preview and GA computer-tool calls. Local execution results still appear as `computer_call_output` items in `new_items`.
+Computer-tool replay follows the raw Responses payload shape. Preview-model `computer_call` items preserve a single `action`, while `gpt-5.5` computer calls can preserve batched `actions[]`. [`to_input_list()`][agents.result.RunResultBase.to_input_list] and [`RunState`][agents.run_state.RunState] keep whichever shape the model produced, so manual replay, pause/resume flows, and stored transcripts continue to work across both preview and GA computer-tool calls. Local execution results still appear as `computer_call_output` items in `new_items`.
 
 ### New items
 

docs/sandbox/guide.md

@@ -555,7 +555,7 @@ async def main(model: str, prompt: str) -> None:
 if __name__ == "__main__":
     asyncio.run(
         main(
-            model="gpt-5.4",
+            model="gpt-5.5",
             prompt=(
                 "Open `repo/task.md`, use the `$credit-note-fixer` skill, fix the bug, "
                 f"run `{TARGET_TEST_CMD}`, and summarize the change."

docs/sandbox_agents.md

@@ -76,7 +76,7 @@ def build_agent(model: str) -> SandboxAgent[None]:
 
 async def main() -> None:
     result = await Runner.run(
-        build_agent("gpt-5.4"),
+        build_agent("gpt-5.5"),
         "Open `repo/task.md`, fix the issue, run the targeted test, and summarize the change.",
         run_config=RunConfig(
             sandbox=SandboxRunConfig(client=UnixLocalSandboxClient()),

docs/scripts/translate_docs.py

@@ -11,7 +11,7 @@
 # logging.basicConfig(level=logging.INFO)
 # logging.getLogger("openai").setLevel(logging.DEBUG)
 
-OPENAI_MODEL = os.environ.get("OPENAI_MODEL", "gpt-5.4")
+OPENAI_MODEL = os.environ.get("OPENAI_MODEL", "gpt-5.5")
 
 ENABLE_CODE_SNIPPET_EXCLUSION = True
 # gpt-4.5 needed this for better quality

docs/streaming.md

@@ -10,7 +10,7 @@ Keep consuming `result.stream_events()` until the async iterator finishes. A str
 
 [`RawResponsesStreamEvent`][agents.stream_events.RawResponsesStreamEvent] are raw events passed directly from the LLM. They are in OpenAI Responses API format, which means each event has a type (like `response.created`, `response.output_text.delta`, etc) and data. These events are useful if you want to stream response messages to the user as soon as they are generated.
 
-Computer-tool raw events keep the same preview-vs-GA distinction as stored results. Preview flows stream `computer_call` items with one `action`, while `gpt-5.4` can stream `computer_call` items with batched `actions[]`. The higher-level [`RunItemStreamEvent`][agents.stream_events.RunItemStreamEvent] surface does not add a special computer-only event name for this: both shapes still surface as `tool_called`, and the screenshot result comes back as `tool_output` wrapping a `computer_call_output` item.
+Computer-tool raw events keep the same preview-vs-GA distinction as stored results. Preview flows stream `computer_call` items with one `action`, while `gpt-5.5` can stream `computer_call` items with batched `actions[]`. The higher-level [`RunItemStreamEvent`][agents.stream_events.RunItemStreamEvent] surface does not add a special computer-only event name for this: both shapes still surface as `tool_called`, and the screenshot result comes back as `tool_output` wrapping a `computer_call_output` item.
 
 For example, this will output the text generated by the LLM token-by-token.
 

docs/tools.md

@@ -93,7 +93,7 @@ crm_tools = tool_namespace(
 
 agent = Agent(
     name="Operations assistant",
-    model="gpt-5.4",
+    model="gpt-5.5",
     instructions="Load the crm namespace before using CRM tools.",
     tools=[*crm_tools, ToolSearchTool()],
 )
@@ -134,7 +134,7 @@ csv_skill: ShellToolSkillReference = {
 
 agent = Agent(
     name="Container shell agent",
-    model="gpt-5.4",
+    model="gpt-5.5",
     instructions="Use the mounted skill when helpful.",
     tools=[
         ShellTool(
@@ -186,20 +186,20 @@ Local runtime tools require you to supply implementations:
 
 `ComputerTool` is still a local harness: you provide a [`Computer`][agents.computer.Computer] or [`AsyncComputer`][agents.computer.AsyncComputer] implementation, and the SDK maps that harness onto the OpenAI Responses API computer surface.
 
-For explicit [`gpt-5.4`](https://developers.openai.com/api/docs/models/gpt-5.4) requests, the SDK sends the GA built-in tool payload `{"type": "computer"}`. The older `computer-use-preview` model keeps the preview payload `{"type": "computer_use_preview", "environment": ..., "display_width": ..., "display_height": ...}`. This mirrors the platform migration described in OpenAI's [Computer use guide](https://developers.openai.com/api/docs/guides/tools-computer-use/):
+For explicit [`gpt-5.5`](https://developers.openai.com/api/docs/models/gpt-5.5) requests, the SDK sends the GA built-in tool payload `{"type": "computer"}`. The older `computer-use-preview` model keeps the preview payload `{"type": "computer_use_preview", "environment": ..., "display_width": ..., "display_height": ...}`. This mirrors the platform migration described in OpenAI's [Computer use guide](https://developers.openai.com/api/docs/guides/tools-computer-use/):
 
--   Model: `computer-use-preview` -> `gpt-5.4`
+-   Model: `computer-use-preview` -> `gpt-5.5`
 -   Tool selector: `computer_use_preview` -> `computer`
 -   Computer call shape: one `action` per `computer_call` -> batched `actions[]` on `computer_call`
 -   Truncation: `ModelSettings(truncation="auto")` required on the preview path -> not required on the GA path
 
-The SDK chooses that wire shape from the effective model on the actual Responses request. If you use a prompt template and the request omits `model` because the prompt owns it, the SDK keeps the preview-compatible computer payload unless you either keep `model="gpt-5.4"` explicit or force the GA selector with `ModelSettings(tool_choice="computer")` or `ModelSettings(tool_choice="computer_use")`.
+The SDK chooses that wire shape from the effective model on the actual Responses request. If you use a prompt template and the request omits `model` because the prompt owns it, the SDK keeps the preview-compatible computer payload unless you either keep `model="gpt-5.5"` explicit or force the GA selector with `ModelSettings(tool_choice="computer")` or `ModelSettings(tool_choice="computer_use")`.
 
 When a [`ComputerTool`][agents.tool.ComputerTool] is present, `tool_choice="computer"`, `"computer_use"`, and `"computer_use_preview"` are all accepted and normalized to the built-in selector that matches the effective request model. Without a `ComputerTool`, those strings still behave like ordinary function names.
 
 This distinction matters when `ComputerTool` is backed by a [`ComputerProvider`][agents.tool.ComputerProvider] factory. The GA `computer` payload does not need `environment` or dimensions at serialization time, so unresolved factories are fine. Preview-compatible serialization still needs a resolved `Computer` or `AsyncComputer` instance so the SDK can send `environment`, `display_width`, and `display_height`.
 
-At runtime, both paths still use the same local harness. Preview responses emit `computer_call` items with a single `action`; `gpt-5.4` can emit batched `actions[]`, and the SDK executes them in order before producing a `computer_call_output` screenshot item. See `examples/tools/computer_use.py` for a runnable Playwright-based harness.
+At runtime, both paths still use the same local harness. Preview responses emit `computer_call` items with a single `action`; `gpt-5.5` can emit batched `actions[]`, and the SDK executes them in order before producing a `computer_call_output` screenshot item. See `examples/tools/computer_use.py` for a runnable Playwright-based harness.
 
 ```python
 from agents import Agent, ApplyPatchTool, ShellTool
@@ -784,7 +784,7 @@ agent = Agent(
             sandbox_mode="workspace-write",
             working_directory="/path/to/repo",
             default_thread_options=ThreadOptions(
-                model="gpt-5.4",
+                model="gpt-5.5",
                 model_reasoning_effort="low",
                 network_access_enabled=True,
                 web_search_mode="disabled",

docs/voice/quickstart.md

@@ -72,15 +72,15 @@ spanish_agent = Agent(
     instructions=prompt_with_handoff_instructions(
         "You're speaking to a human, so be polite and concise. Speak in Spanish.",
     ),
-    model="gpt-5.4",
+    model="gpt-5.5",
 )
 
 agent = Agent(
     name="Assistant",
     instructions=prompt_with_handoff_instructions(
         "You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.",
     ),
-    model="gpt-5.4",
+    model="gpt-5.5",
     handoffs=[spanish_agent],
     tools=[get_weather],
 )
@@ -156,15 +156,15 @@ spanish_agent = Agent(
     instructions=prompt_with_handoff_instructions(
         "You're speaking to a human, so be polite and concise. Speak in Spanish.",
     ),
-    model="gpt-5.4",
+    model="gpt-5.5",
 )
 
 agent = Agent(
     name="Assistant",
     instructions=prompt_with_handoff_instructions(
         "You're speaking to a human, so be polite and concise. If the user speaks in Spanish, handoff to the spanish agent.",
     ),
-    model="gpt-5.4",
+    model="gpt-5.5",
     handoffs=[spanish_agent],
     tools=[get_weather],
 )

examples/basic/hello_world_gpt_5.py

@@ -9,14 +9,14 @@
 # from openai import AsyncOpenAI
 # client = AsyncOpenAI()
 # from agents import OpenAIChatCompletionsModel
-# chat_completions_model = OpenAIChatCompletionsModel(model="gpt-5.4", openai_client=client)
+# chat_completions_model = OpenAIChatCompletionsModel(model="gpt-5.5", openai_client=client)
 
 
 async def main():
     agent = Agent(
         name="Knowledgable GPT-5 Assistant",
         instructions="You're a knowledgable assistant. You always provide an interesting answer.",
-        model="gpt-5.4",
+        model="gpt-5.5",
         model_settings=ModelSettings(
             reasoning=Reasoning(effort="low"),  # "none", "low", "medium", "high", "xhigh"
             verbosity="low",  # "low", "medium", "high"