Fix paths in docs

Signed-off-by: Víctor Mayoral Vilches <v.mayoralv@gmail.com>

docs/agents.md

@@ -11,7 +11,7 @@ The most common properties of an agent you'll configure are:
 -   `tools`: Tools that the agent can use to achieve its tasks.
 
 ```python
-from cai.agents import Agent, ModelSettings, function_tool
+from cai.sdk.agents import Agent, ModelSettings, function_tool
 
 @function_tool
 def get_weather(city: str) -> str:
@@ -49,7 +49,7 @@ By default, agents produce plain text (i.e. `str`) outputs. If you want the agen
 
 ```python
 from pydantic import BaseModel
-from cai.agents import Agent
+from cai.sdk.agents import Agent
 
 
 class CalendarEvent(BaseModel):
@@ -73,7 +73,7 @@ agent = Agent(
 Handoffs are sub-agents that the agent can delegate to. You provide a list of handoffs, and the agent can choose to delegate to them if relevant. This is a powerful pattern that allows orchestrating modular, specialized agents that excel at a single task. Read more in the [handoffs](handoffs.md) documentation.
 
 ```python
-from cai.agents import Agent
+from cai.sdk.agents import Agent
 
 booking_agent = Agent(...)
 refund_agent = Agent(...)

docs/config.md

@@ -5,7 +5,7 @@
 By default, the SDK looks for the `OPENAI_API_KEY` environment variable for LLM requests and tracing, as soon as it is imported. If you are unable to set that environment variable before your app starts, you can use the [`set_default_openai_key()`][cai.sdk.agents.set_default_openai_key] function to set the key.
 
 ```python
-from cai.agents import set_default_openai_key
+from cai.sdk.agents import set_default_openai_key
 
 set_default_openai_key("sk-...")
 ```
@@ -14,7 +14,7 @@ Alternatively, you can also configure an OpenAI client to be used. By default, t
 
 ```python
 from openai import AsyncOpenAI
-from cai.agents import set_default_openai_client
+from cai.sdk.agents import set_default_openai_client
 
 custom_client = AsyncOpenAI(base_url="...", api_key="...")
 set_default_openai_client(custom_client)
@@ -23,7 +23,7 @@ set_default_openai_client(custom_client)
 Finally, you can also customize the OpenAI API that is used. By default, we use the OpenAI Responses API. You can override this to use the Chat Completions API by using the [`set_default_openai_api()`][cai.sdk.agents.set_default_openai_api] function.
 
 ```python
-from cai.agents import set_default_openai_api
+from cai.sdk.agents import set_default_openai_api
 
 set_default_openai_api("chat_completions")
 ```
@@ -33,7 +33,7 @@ set_default_openai_api("chat_completions")
 Tracing is enabled by default. It uses the OpenAI API keys from the section above by default (i.e. the environment variable or the default key you set). You can specifically set the API key used for tracing by using the [`set_tracing_export_api_key`][cai.sdk.agents.set_tracing_export_api_key] function.
 
 ```python
-from cai.agents import set_tracing_export_api_key
+from cai.sdk.agents import set_tracing_export_api_key
 
 set_tracing_export_api_key("sk-...")
 ```
@@ -41,7 +41,7 @@ set_tracing_export_api_key("sk-...")
 You can also disable tracing entirely by using the [`set_tracing_disabled()`][cai.sdk.agents.set_tracing_disabled] function.
 
 ```python
-from cai.agents import set_tracing_disabled
+from cai.sdk.agents import set_tracing_disabled
 
 set_tracing_disabled(True)
 ```
@@ -53,7 +53,7 @@ The SDK has two Python loggers without any handlers set. By default, this means
 To enable verbose logging, use the [`enable_verbose_stdout_logging()`][cai.sdk.agents.enable_verbose_stdout_logging] function.
 
 ```python
-from cai.agents import enable_verbose_stdout_logging
+from cai.sdk.agents import enable_verbose_stdout_logging
 
 enable_verbose_stdout_logging()
 ```

docs/context.md

@@ -29,7 +29,7 @@ You can use the context for things like:
 import asyncio
 from dataclasses import dataclass
 
-from cai.agents import Agent, RunContextWrapper, Runner, function_tool
+from cai.sdk.agents import Agent, RunContextWrapper, Runner, function_tool
 
 @dataclass
 class UserInfo:  # (1)!

docs/guardrails.md

@@ -41,7 +41,7 @@ You need to provide a function that receives input, and returns a [`GuardrailFun
 
 ```python
 from pydantic import BaseModel
-from cai.agents import (
+from cai.sdk.agents import (
     Agent,
     GuardrailFunctionOutput,
     InputGuardrailTripwireTriggered,
@@ -99,7 +99,7 @@ Output guardrails are similar.
 
 ```python
 from pydantic import BaseModel
-from cai.agents import (
+from cai.sdk.agents import (
     Agent,
     GuardrailFunctionOutput,
     OutputGuardrailTripwireTriggered,

docs/handoffs.md

@@ -15,7 +15,7 @@ You can create a handoff using the [`handoff()`][cai.sdk.agents.handoffs.handoff
 Here's how you can create a simple handoff:
 
 ```python
-from cai.agents import Agent, handoff
+from cai.sdk.agents import Agent, handoff
 
 billing_agent = Agent(name="Billing agent")
 refund_agent = Agent(name="Refund agent")
@@ -38,7 +38,7 @@ The [`handoff()`][cai.sdk.agents.handoffs.handoff] function lets you customize t
 -   `input_filter`: This lets you filter the input received by the next agent. See below for more.
 
 ```python
-from cai.agents import Agent, handoff, RunContextWrapper
+from cai.sdk.agents import Agent, handoff, RunContextWrapper
 
 def on_handoff(ctx: RunContextWrapper[None]):
     print("Handoff called")
@@ -60,7 +60,7 @@ In certain situations, you want the LLM to provide some data when it calls a han
 ```python
 from pydantic import BaseModel
 
-from cai.agents import Agent, handoff, RunContextWrapper
+from cai.sdk.agents import Agent, handoff, RunContextWrapper
 
 class EscalationData(BaseModel):
     reason: str
@@ -84,7 +84,7 @@ When a handoff occurs, it's as though the new agent takes over the conversation,
 There are some common patterns (for example removing all tool calls from the history), which are implemented for you in [`cai.sdk.agents.extensions.handoff_filters`][]
 
 ```python
-from cai.agents import Agent, handoff
+from cai.sdk.agents import Agent, handoff
 from agents.extensions import handoff_filters
 
 agent = Agent(name="FAQ agent")
@@ -102,7 +102,7 @@ handoff_obj = handoff(
 To make sure that LLMs understand handoffs properly, we recommend including information about handoffs in your agents. We have a suggested prefix in [`cai.sdk.agents.extensions.handoff_prompt.RECOMMENDED_PROMPT_PREFIX`][], or you can call [`cai.sdk.agents.extensions.handoff_prompt.prompt_with_handoff_instructions`][] to automatically add recommended data to your prompts.
 
 ```python
-from cai.agents import Agent
+from cai.sdk.agents import Agent
 from agents.extensions.handoff_prompt import RECOMMENDED_PROMPT_PREFIX
 
 billing_agent = Agent(

docs/index.md

@@ -33,7 +33,7 @@ pip install openai-agents
 ## Hello world example
 
 ```python
-from cai.agents import Agent, Runner
+from cai.sdk.agents import Agent, Runner
 
 agent = Agent(name="Assistant", instructions="You are a helpful assistant")
 

docs/models.md

@@ -18,7 +18,7 @@ Within a single workflow, you may want to use different models for each agent. F
     While our SDK supports both the [`OpenAIResponsesModel`][cai.sdk.agents.models.openai_responses.OpenAIResponsesModel] and the [`OpenAIChatCompletionsModel`][cai.sdk.agents.models.openai_chatcompletions.OpenAIChatCompletionsModel] shapes, we recommend using a single model shape for each workflow because the two shapes support a different set of features and tools. If your workflow requires mixing and matching model shapes, make sure that all the features you're using are available on both.
 
 ```python
-from cai.agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel
+from cai.sdk.agents import Agent, Runner, AsyncOpenAI, OpenAIChatCompletionsModel
 import asyncio
 
 spanish_agent = Agent(

docs/quickstart.md

@@ -37,7 +37,7 @@ export OPENAI_API_KEY=sk-...
 Agents are defined with instructions, a name, and optional config (such as `model_config`)
 
 ```python
-from cai.agents import Agent
+from cai.sdk.agents import Agent
 
 agent = Agent(
     name="Math Tutor",
@@ -50,7 +50,7 @@ agent = Agent(
 Additional agents can be defined in the same way. `handoff_descriptions` provide additional context for determining handoff routing
 
 ```python
-from cai.agents import Agent
+from cai.sdk.agents import Agent
 
 history_tutor_agent = Agent(
     name="History Tutor",
@@ -82,7 +82,7 @@ triage_agent = Agent(
 Let's check that the workflow runs and the triage agent correctly routes between the two specialist agents.
 
 ```python
-from cai.agents import Runner
+from cai.sdk.agents import Runner
 
 async def main():
     result = await Runner.run(triage_agent, "What is the capital of France?")
@@ -94,7 +94,7 @@ async def main():
 You can define custom guardrails to run on the input or output.
 
 ```python
-from cai.agents import GuardrailFunctionOutput, Agent, Runner
+from cai.sdk.agents import GuardrailFunctionOutput, Agent, Runner
 from pydantic import BaseModel
 
 class HomeworkOutput(BaseModel):
@@ -121,7 +121,7 @@ async def homework_guardrail(ctx, agent, input_data):
 Let's put it all together and run the entire workflow, using handoffs and the input guardrail.
 
 ```python
-from cai.agents import Agent, InputGuardrail,GuardrailFunctionOutput, Runner
+from cai.sdk.agents import Agent, InputGuardrail,GuardrailFunctionOutput, Runner
 from pydantic import BaseModel
 import asyncio
 

docs/running_agents.md

@@ -7,7 +7,7 @@ You can run agents via the [`Runner`][cai.sdk.agents.run.Runner] class. You have
 3. [`Runner.run_streamed()`][cai.sdk.agents.run.Runner.run_streamed], which runs async and returns a [`RunResultStreaming`][cai.sdk.agents.result.RunResultStreaming]. It calls the LLM in streaming mode, and streams those events to you as they are received.
 
 ```python
-from cai.agents import Agent, Runner
+from cai.sdk.agents import Agent, Runner
 
 async def main():
     agent = Agent(name="Assistant", instructions="You are a helpful assistant")

docs/streaming.md

@@ -13,7 +13,7 @@ For example, this will output the text generated by the LLM token-by-token.
 ```python
 import asyncio
 from openai.types.responses import ResponseTextDeltaEvent
-from cai.agents import Agent, Runner
+from cai.sdk.agents import Agent, Runner
 
 async def main():
     agent = Agent(
@@ -40,7 +40,7 @@ For example, this will ignore raw events and stream updates to the user.
 ```python
 import asyncio
 import random
-from cai.agents import Agent, ItemHelpers, Runner, function_tool
+from cai.sdk.agents import Agent, ItemHelpers, Runner, function_tool
 
 @function_tool
 def how_many_jokes() -> int:

docs/tools.md

@@ -15,7 +15,7 @@ OpenAI offers a few built-in tools when using the [`OpenAIResponsesModel`][cai.s
 -   The [`ComputerTool`][cai.sdk.agents.tool.ComputerTool] allows automating computer use tasks.
 
 ```python
-from cai.agents import Agent, FileSearchTool, Runner, WebSearchTool
+from cai.sdk.agents import Agent, FileSearchTool, Runner, WebSearchTool
 
 agent = Agent(
     name="Assistant",
@@ -49,7 +49,7 @@ import json
 
 from typing_extensions import TypedDict, Any
 
-from cai.agents import Agent, FunctionTool, RunContextWrapper, function_tool
+from cai.sdk.agents import Agent, FunctionTool, RunContextWrapper, function_tool
 
 
 class Location(TypedDict):
@@ -183,7 +183,7 @@ from typing import Any
 
 from pydantic import BaseModel
 
-from cai.agents import RunContextWrapper, FunctionTool
+from cai.sdk.agents import RunContextWrapper, FunctionTool
 
 
 
@@ -223,7 +223,7 @@ The code for the schema extraction lives in [`cai.sdk.agents.function_schema`][]
 In some workflows, you may want a central agent to orchestrate a network of specialized agents, instead of handing off control. You can do this by modeling agents as tools.
 
 ```python
-from cai.agents import Agent, Runner
+from cai.sdk.agents import Agent, Runner
 import asyncio
 
 spanish_agent = Agent(

docs/tracing.md

@@ -48,7 +48,7 @@ In addition, you can set up [custom trace processors](#custom-tracing-processors
 Sometimes, you might want multiple calls to `run()` to be part of a single trace. You can do this by wrapping the entire code in a `trace()`.
 
 ```python
-from cai.agents import Agent, Runner, trace
+from cai.sdk.agents import Agent, Runner, trace
 
 async def main():
     agent = Agent(name="Joke generator", instructions="Tell funny jokes.")

docs/voice/quickstart.md

@@ -50,7 +50,7 @@ First, let's set up some Agents. This should feel familiar to you if you've buil
 import asyncio
 import random
 
-from cai.agents import (
+from cai.sdk.agents import (
     Agent,
     function_tool,
 )
@@ -129,7 +129,7 @@ import random
 import numpy as np
 import sounddevice as sd
 
-from cai.agents import (
+from cai.sdk.agents import (
     Agent,
     function_tool,
     set_tracing_disabled,