Fix stale docs and align conventions across the AI samples

.github/CODEOWNERS

@@ -1,5 +1,4 @@
 * @temporalio/sdk
-/langgraph_plugin/ @temporalio/sdk @temporalio/ai-sdk
 
 # SDK & Nexus own the README, pyproject.toml, and uv.lock
 /README.md @temporalio/sdk @temporalio/nexus

README.md

@@ -7,8 +7,10 @@ This is a collection of samples showing how to use the [Python SDK](https://gith
 Prerequisites:
 
 * [uv](https://docs.astral.sh/uv/)
-* [Temporal CLI installed](https://docs.temporal.io/cli#install)
-* [Local Temporal server running](https://docs.temporal.io/cli/server#start-dev)
+* [Temporal CLI](https://docs.temporal.io/cli) with a local dev server running:
+  ```
+  temporal server start-dev
+  ```
 
 The SDK requires Python >= 3.10. You can install Python using uv. For example,
 

bedrock/README.md

@@ -12,7 +12,11 @@ Demonstrates how Temporal and Amazon Bedrock can be used to quickly build bullet
 
 1. An AWS account with Bedrock enabled.
 2. A machine that has access to Bedrock.
-3. A local Temporal server running on the same machine. See [Temporal's dev server docs](https://docs.temporal.io/cli#start-dev-server) for more information.
+3. A local Temporal server running on the same machine, started with the [Temporal CLI](https://docs.temporal.io/cli):
+
+   ```
+   temporal server start-dev
+   ```
 
 These examples use Amazon's Python SDK (Boto3). To configure Boto3 to use your AWS credentials, follow the instructions in [the Boto3 documentation](https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html).
 

external_storage/README.md

@@ -25,7 +25,7 @@ on demand for the Temporal Web UI.
 ## Prerequisites
 
 * [uv](https://docs.astral.sh/uv/)
-* [Temporal CLI](https://docs.temporal.io/cli#install) with a local dev server running:
+* [Temporal CLI](https://docs.temporal.io/cli) with a local dev server running:
   ```
   temporal server start-dev
   ```

google_adk_agents/README.md

@@ -23,7 +23,10 @@ model turn is durable and observable.
 
 ## Prerequisites
 
-- Temporal server [running locally](https://docs.temporal.io/cli/server#start-dev)
+- [Temporal CLI](https://docs.temporal.io/cli) with a local dev server running:
+  ```
+  temporal server start-dev
+  ```
 - Dependencies installed via `uv sync --group google-adk`
 - Google API key set as an environment variable:
   `export GOOGLE_API_KEY=your_key_here`
@@ -49,6 +52,6 @@ To run any scenario, start its worker in one terminal and its workflow starter
 in another:
 
 ```bash
-uv run python -m google_adk_agents.<scenario>.run_worker
-uv run python -m google_adk_agents.<scenario>.run_<name>_workflow
+uv run google_adk_agents/<scenario>/run_worker.py
+uv run google_adk_agents/<scenario>/run_<name>_workflow.py
 ```

google_adk_agents/agent_patterns/README.md

@@ -15,13 +15,13 @@ Before running, review the [prerequisites in the suite README](../README.md)
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.agent_patterns.run_worker
+uv run google_adk_agents/agent_patterns/run_worker.py
 ```
 
 Then start the workflow in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.agent_patterns.run_multi_agent_workflow
+uv run google_adk_agents/agent_patterns/run_multi_agent_workflow.py
 ```
 
 ## What to expect

google_adk_agents/agent_patterns/run_multi_agent_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -9,7 +10,10 @@
 
 
 async def main():
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     result = await client.execute_workflow(
         MultiAgentWorkflow.run,

google_adk_agents/agent_patterns/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -14,7 +15,9 @@
 async def main():
     plugin = GoogleAdkPlugin()
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

google_adk_agents/basic/README.md

@@ -17,13 +17,13 @@ Before running, review the [prerequisites in the suite README](../README.md)
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.basic.run_worker
+uv run google_adk_agents/basic/run_worker.py
 ```
 
 Then start the workflow in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.basic.run_hello_world_workflow
+uv run google_adk_agents/basic/run_hello_world_workflow.py
 ```
 
 ## What to expect

google_adk_agents/basic/run_hello_world_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -10,7 +11,10 @@
 
 async def main():
     # @@@SNIPSTART google-adk-agents-basic-starter
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     result = await client.execute_workflow(
         HelloWorldAgentWorkflow.run,

google_adk_agents/basic/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -15,7 +16,9 @@ async def main():
     # @@@SNIPSTART google-adk-agents-basic-worker
     plugin = GoogleAdkPlugin()
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

google_adk_agents/chatbot/README.md

@@ -21,13 +21,13 @@ Before running, review the [prerequisites in the suite README](../README.md)
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.chatbot.run_worker
+uv run google_adk_agents/chatbot/run_worker.py
 ```
 
 Then start the interactive client in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.chatbot.run_chatbot_workflow
+uv run google_adk_agents/chatbot/run_chatbot_workflow.py
 ```
 
 ## What to expect

google_adk_agents/chatbot/run_chatbot_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -10,7 +11,10 @@
 
 async def main():
     # @@@SNIPSTART google-adk-agents-chatbot-starter
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     handle = await client.start_workflow(
         ChatbotAgentWorkflow.run,

google_adk_agents/chatbot/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -15,7 +16,9 @@ async def main():
     # @@@SNIPSTART google-adk-agents-chatbot-worker
     plugin = GoogleAdkPlugin()
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

google_adk_agents/mcp/README.md

@@ -28,13 +28,13 @@ server, `uv sync --group google-adk`, and `export GOOGLE_API_KEY=...`).
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.mcp.run_worker
+uv run google_adk_agents/mcp/run_worker.py
 ```
 
 Then start the workflow in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.mcp.run_echo_workflow
+uv run google_adk_agents/mcp/run_echo_workflow.py
 ```
 
 The worker spawns `echo_mcp_server.py` itself; you don't need to start it

google_adk_agents/mcp/run_echo_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -7,7 +8,10 @@
 
 
 async def main():
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     result = await client.execute_workflow(
         EchoMcpWorkflow.run,

google_adk_agents/mcp/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import (
@@ -19,7 +20,9 @@ async def main():
         toolset_providers=[TemporalMcpToolSetProvider("echo", echo_toolset)]
     )
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

google_adk_agents/streaming/README.md

@@ -18,13 +18,13 @@ Before running, review the [prerequisites in the suite README](../README.md)
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.streaming.run_worker
+uv run google_adk_agents/streaming/run_worker.py
 ```
 
 Then start the workflow in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.streaming.run_streaming_workflow
+uv run google_adk_agents/streaming/run_streaming_workflow.py
 ```
 
 ## What to expect

google_adk_agents/streaming/run_streaming_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 from datetime import timedelta
 
 from google.adk.models.llm_response import LlmResponse
@@ -14,7 +15,10 @@
 
 
 async def main():
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     handle = await client.start_workflow(
         StreamingAgentWorkflow.run,

google_adk_agents/streaming/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -14,7 +15,9 @@
 async def main():
     plugin = GoogleAdkPlugin()
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

google_adk_agents/tools/README.md

@@ -14,13 +14,13 @@ Before running, review the [prerequisites in the suite README](../README.md)
 Start the worker in one terminal:
 
 ```bash
-uv run python -m google_adk_agents.tools.run_worker
+uv run google_adk_agents/tools/run_worker.py
 ```
 
 Then start the workflow in another terminal:
 
 ```bash
-uv run python -m google_adk_agents.tools.run_weather_workflow
+uv run google_adk_agents/tools/run_weather_workflow.py
 ```
 
 ## What to expect

google_adk_agents/tools/run_weather_workflow.py

@@ -1,4 +1,5 @@
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -7,7 +8,10 @@
 
 
 async def main():
-    client = await Client.connect("localhost:7233", plugins=[GoogleAdkPlugin()])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"),
+        plugins=[GoogleAdkPlugin()],
+    )
 
     result = await client.execute_workflow(
         WeatherAgentWorkflow.run,

google_adk_agents/tools/run_worker.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 
 from temporalio.client import Client
 from temporalio.contrib.google_adk_agents import GoogleAdkPlugin
@@ -14,7 +15,9 @@ async def main():
     # @@@SNIPSTART google-adk-agents-tools-worker
     plugin = GoogleAdkPlugin()
 
-    client = await Client.connect("localhost:7233", plugins=[plugin])
+    client = await Client.connect(
+        os.environ.get("TEMPORAL_ADDRESS", "localhost:7233"), plugins=[plugin]
+    )
 
     worker = Worker(
         client,

langgraph_plugin/README.md

@@ -27,7 +27,7 @@ Samples are organized by API style:
    uv sync --group langgraph
    ```
 
-2. Start a [Temporal dev server](https://docs.temporal.io/cli#start-dev-server):
+2. Start a local dev server with the [Temporal CLI](https://docs.temporal.io/cli):
 
    ```bash
    temporal server start-dev

langgraph_plugin/graph_api/streaming/README.md

@@ -1,6 +1,6 @@
 # Streaming (Graph API)
 
-Streams a LangGraph run to an external client while the workflow is still running, using Temporal's durable, offset-addressed [`WorkflowStream`](https://docs.temporal.io/). The graph writes a short story about a topic and emits both fine-grained tokens and node-completion progress on separate topics.
+Streams a LangGraph run to an external client while the workflow is still running, using Temporal's durable, offset-addressed [`WorkflowStream`](https://github.com/temporalio/sdk-python/tree/main/temporalio/contrib/workflow_streams). The graph writes a short story about a topic and emits both fine-grained tokens and node-completion progress on separate topics.
 
 ## What This Sample Demonstrates