Update framework documentation

README.md

@@ -35,7 +35,7 @@ async def contact_mothership(query: str) -> str:
 
 
 async def main() -> None:
-    model = ai.get_model("gateway:anthropic/claude-sonnet-4")
+    model = ai.get_model("anthropic/claude-sonnet-4")
     agent = ai.agent(tools=[contact_mothership])
 
     messages = [
@@ -105,7 +105,7 @@ Built-in tools execute on the provider side and arrive as part of the stream:
 async with ai.stream(
     model,
     [ai.user_message("Latest Formula 1 results?")],
-    tools=[ai.anthropic.tools.web_search(max_uses=3)],
+    tools=[ai.providers.anthropic.tools.web_search(max_uses=3)],
 ) as s:
     async for event in s:
         if isinstance(event, ai.events.TextDelta):

docs/ai-python/content/docs/basics/agents.mdx

@@ -6,30 +6,16 @@ summary: Create agents, run the default loop, inspect results, and understand mu
 ---
 
 Use an agent when the model needs to call tools and continue with the tool
-results. The default agent loop is built from the same primitives you can use
-directly: `ai.stream`, `ToolRunner`, messages, and events.
+results.
 
 ## Create an agent
 
 An agent wraps `ai.stream` in a loop. It streams model output, executes requested
 tools, appends tool results to history, and repeats until the model returns a
 final assistant message.
 
-```python
-agent = ai.agent(tools=[contact_mothership])
-
-async with agent.run(model, messages) as stream:
-    async for event in stream:
-        if isinstance(event, ai.events.TextDelta):
-            print(event.chunk, end="", flush=True)
-```
-
-Use `ai.agent` for the default loop. Subclass `ai.Agent` and override
-`async def loop()` when you need to change control flow.
-
-## Run the default loop
-
-Create an agent with tools, then call `agent.run`:
+Subclass `ai.Agent` and override `async def loop()` when you need to change
+control flow.
 
 ```python title="agent_loop.py"
 import asyncio
@@ -64,17 +50,19 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-## Inspect the run result
-
 The stream yields model events and agent events. After the run finishes,
 `stream.messages` contains the updated history, and `stream.output` contains
 the final assistant output.
 
+Unline `ai.stream`, every `agent.run` can produce multiple messages alternating
+between `"user"`/`"tool"` and `"assistant"`, representing turns in the LLM request
+and response cycle.
+
 ## Understand multi-turn behavior
 
-Each loop turn streams one assistant message. If the message contains tool
-calls, the agent executes them, appends one tool-result message, and starts the
-next model turn.
+Each loop turn has one `ai.stream` that produces one assistant message. If the 
+message contains tool calls, the agent executes them, appends one tool-result 
+message, and starts the next model turn.
 
 ```python
 async with agent.run(model, messages) as stream:
@@ -109,7 +97,7 @@ async with agent.run(
     model,
     [ai.user_message("Return a JSON mothership forecast.")],
     output_type=Forecast,
-    params={"temperature": 0},
+    params=ai.InferenceRequestParams().with_temperature(0),
 ) as stream:
     async for event in stream:
         if isinstance(event, ai.events.TextDelta):
@@ -118,22 +106,3 @@ async with agent.run(
 forecast = stream.output
 print(forecast.eta)
 ```
-
-## Choose agents or direct streaming
-
-Use `ai.stream` when you want one model response and you will handle any tool
-calls yourself. Use an agent when the SDK should execute Python tools, append
-tool results, and keep looping until the assistant returns a final answer.
-
-```python
-# Direct stream: inspect tool calls yourself.
-async with ai.stream(model, messages, tools=[get_weather.tool]) as stream:
-    async for event in stream:
-        ...
-
-# Agent: execute registered tools.
-agent = ai.agent(tools=[get_weather])
-async with agent.run(model, messages) as stream:
-    async for event in stream:
-        ...
-```

docs/ai-python/content/docs/basics/ai-sdk-ui.mdx

@@ -5,42 +5,18 @@ type: guide
 summary: Parse UI messages, apply approvals, stream SSE responses, set headers, and rebuild UI history.
 ---
 
-The AI SDK UI adapter converts between AI SDK UI messages and the Python
-runtime message/event types.
+This adapter provides integration with the UI part of the sister AI SDK
+in TypeScript.
 
-## Parse UI messages
+AI SDK UI provides `useChat`, which handles streaming complexity on the
+client side, such as collecting message chunks and optimistically updating
+the UI when the user submits a new message.
 
-Accept `UIMessage` values from an AI SDK UI client, then convert them to
-runtime messages:
+The AI SDK UI's data model is significantly different from the AI SDK for 
+Python's, which is why you need to convert events and messages back and forth
+using the adapter.
 
-```python
-class ChatRequest(pydantic.BaseModel):
-    messages: list[ai.agents.ui.ai_sdk.UIMessage]
-
-
-@app.post("/chat")
-async def chat(request: ChatRequest):
-    messages, approvals = ai.agents.ui.ai_sdk.to_messages(request.messages)
-```
-
-`to_messages` also extracts approval responses from tool parts.
-
-## Apply approval responses
-
-Register extracted approvals before resuming the agent:
-
-```python
-messages, approvals = ai.agents.ui.ai_sdk.to_messages(request.messages)
-ai.agents.ui.ai_sdk.apply_approvals(approvals)
-
-async with chat_agent.run(model, messages) as stream:
-    ...
-```
-
-The hook registry stores each approval until the matching tool-approval hook
-runs.
-
-## Stream SSE responses
+## Outbound streaming and message history
 
 Use `to_sse` to convert agent events to AI SDK UI stream chunks:
 
@@ -61,18 +37,6 @@ async def chat(request: ChatRequest) -> fastapi.responses.StreamingResponse:
     )
 ```
 
-## Set response headers
-
-Return the adapter headers on every streamed response:
-
-```python
-headers = ai.agents.ui.ai_sdk.UI_MESSAGE_STREAM_HEADERS
-```
-
-These headers identify the response as an AI SDK UI message stream.
-
-## Rebuild UI history
-
 Convert stored runtime messages back to AI SDK UI messages for history
 endpoints:
 
@@ -86,8 +50,6 @@ async def get_chat(session_id: str):
 The adapter groups assistant, tool, and internal hook messages into one
 assistant UI message.
 
-## Support streaming tool output
-
 Generator tools and subagents emit `PartialToolCallResult` events. The UI
 adapter folds those partial values into the corresponding tool output:
 
@@ -101,4 +63,37 @@ async def draft_mothership_reply(topic: str) -> ai.StreamingTextTool:
 ```
 
 For subagents, `ai.SubAgentTool` streams nested events and stores the nested
-assistant message as the tool output.
+transcript as a `MessageBundle`. The model sees the nested agent's final
+assistant text.
+
+## Inbound message updates
+
+Accept `UIMessage` values from an AI SDK UI client, then convert them to
+runtime messages:
+
+```python
+class ChatRequest(pydantic.BaseModel):
+    messages: list[ai.agents.ui.ai_sdk.UIMessage]
+
+
+@app.post("/chat")
+async def chat(request: ChatRequest):
+    messages, approvals = ai.agents.ui.ai_sdk.to_messages(request.messages)
+```
+
+`to_messages` also extracts approval responses from tool parts.
+
+## Tool approvals
+
+Register extracted approvals before resuming the agent:
+
+```python
+messages, approvals = ai.agents.ui.ai_sdk.to_messages(request.messages)
+ai.agents.ui.ai_sdk.apply_approvals(approvals)
+
+async with chat_agent.run(model, messages) as stream:
+    ...
+```
+
+The hook registry stores each approval until the matching tool-approval hook
+runs.

docs/ai-python/content/docs/basics/custom-loops.mdx

@@ -5,104 +5,51 @@ type: guide
 summary: Override the agent loop to customize scheduling, routing, history updates, logging, and tool execution.
 ---
 
-Custom loops use the same primitives as the default loop. Override `Agent.loop`
-when you need to change scheduling, logging, routing, or persistence.
+Override `loop` when you need custom tool dispatch, logging, durability, or
+branching. While the SDK defines the loop as a Python async generator, it still
+uses a few framework components. Reuse those to retain framework-controlled
+behavior.
 
-## When to customize the loop
+## Explore the standard loop shape
 
-Override `loop` when you need custom scheduling, logging, durability, or
-branching. Keep the same pattern when you still want SDK-managed history and
-tool resolution.
-
-## Use the standard loop shape
-
-The default loop keeps running while the last message needs more work. On each
+The default loop keeps running while there is more work to do. On each
 turn, it streams the model response and schedules tool calls:
 
 ```python
 class CustomAgent(ai.Agent):
-    async def loop(self, context: ai.Context):
+    # ai.Context keeps track of message history, run inputs, and other per-run data
+    async def loop(self, context: ai.Context) -> AsyncGenerator[ai.events.AgentEvent]:
         while context.keep_running():
+            # call ai.stream with whatever model, tools, and messages the user has
+            # passed to agent.run
             async with (
                 ai.stream(context=context) as stream,
+                # ai.ToolRunner is responsible for concurrent tool scheduling and
+                # streaming, as well as graceful handling of hook interruptions
                 ai.ToolRunner() as tool_runner,
+
             ):
+                # ai.util.merge interleaves two streams together, so the agent
+                # can fire off tools as they arrive in the stream rather than
+                # waiting for the model to stop streaming; and also start streaming
+                # the streaming tools.
                 async for event in ai.util.merge(stream, tool_runner.events()):
                     yield event
 
                     if isinstance(event, ai.events.ToolEnd):
+                        # context.resolve looks up the Python function for the
+                        # tool name in the model's tool call
                         tool_call = context.resolve(event.tool_call)
+                        # schedule the tool for concurrent execution
+                        # using the tool runner
                         tool_runner.schedule(tool_call)
 
+                # add new messages to message history stored in the context.
+                # this works with internal replay machinery to enable serverless
+                # execution.
                 context.add(stream.message)
                 context.add(tool_runner.get_tool_message())
 ```
 
-## Resolve and schedule tool calls
-
-`ToolEnd` means the model finished emitting a tool call. Resolve it through the
-context, then schedule it with `ToolRunner`:
-
-```python
-if isinstance(event, ai.events.ToolEnd):
-    tool_call = context.resolve(event.tool_call)
-    tool_runner.schedule(tool_call)
-```
-
-`context.resolve` validates that the agent has an executable tool registered
-for the model's `tool_name`.
-
-## Add messages to history
-
-After a stream turn finishes, add the assistant message and any tool-result
-message:
-
-```python
-context.add(stream.message)
-context.add(tool_runner.get_tool_message())
-```
-
-`context.add` skips replayed assistant messages, so resume flows can call it
-without duplicating history.
-
-## Run tools sequentially
-
-`ToolRunner.schedule` runs active tools concurrently. To run tools one at a
-time, collect the calls during the model stream, then execute them in order:
-
-```python
-pending: list[ai.ToolCall] = []
-
-async for event in stream:
-    yield event
-    if isinstance(event, ai.events.ToolEnd):
-        pending.append(context.resolve(event.tool_call))
-
-for tool_call in pending:
-    result = await tool_call()
-    yield result
-    tool_runner.add_result(result)
-```
-
-This keeps the same tool-message aggregation path while preserving execution
-order.
-
-## Add logging or routing
-
-Custom loops can inspect events before yielding or scheduling:
-
-```python
-if isinstance(event, ai.events.ToolEnd):
-    call = event.tool_call
-    print(f"tool: {call.tool_name}({call.tool_args})")
-    tool_runner.schedule(context.resolve(call))
-```
-
-You can also route specific tools through custom wrappers:
-
-```python
-if tool_call.name == "contact_mothership":
-    tool_runner.schedule(GatedToolCall(tool_call))
-else:
-    tool_runner.schedule(tool_call)
-```
+You can modify most of the loop and extend `CustomAgent` to fit your application's needs, 
+and the SDK will keep working as long as the loop is still an async generator of events.