[docs]: add auth and small changes (#1356)

* wip

* m

* nit

docs/docs/cloud/deployment/test_locally.md

@@ -38,6 +38,46 @@ Ready!
 
 We can now interact with the API server using the LangGraph SDK. First, we need to start our client, select our assistant (in this case a graph we called "agent", make sure to select the proper assistant you wish to test).
 
+You can either initialize by passing authentication or by setting an environment variable.
+
+#### Initialize with authentication
+
+=== "Python"
+
+    ```python
+    from langgraph_sdk import get_client
+
+    # only pass the url argument to get_client() if you changed the default port when calling langgraph up
+    client = get_client(url=<DEPLOYMENT_URL>,api_key=<LANGCHAIN_API_KEY>)
+    assistant_id = "agent"
+    thread = await client.threads.create()
+    ```
+
+=== "Javascript"
+
+    ```js
+    import { Client } from "@langchain/langgraph-sdk";
+
+    // only set the apiUrl if you changed the default port when calling langgraph up
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL>, apiKey: <LANGCHAIN_API_KEY> });
+    const assistantId = "agent"
+    const thread = await client.threads.create();
+    ```
+
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json'
+      --header 'x-api-key: <LANGCHAIN_API_KEY>'
+    ```
+  
+
+#### Initialize with environment variables
+
+If you have a `LANGCHAIN_API_KEY` set in your environment, you do not need to explicitly pass authentication to the client
+
 === "Python"
 
     ```python
@@ -60,6 +100,14 @@ We can now interact with the API server using the LangGraph SDK. First, we need
     const thread = await client.threads.create();
     ```
 
+=== "CURL"
+
+    ```bash
+    curl --request POST \
+      --url <DEPLOYMENT_URL>/threads \
+      --header 'Content-Type: application/json'
+    ```
+
 Now we can invoke our graph to ensure it is working. Make sure to change the input to match the proper schema for your graph. 
 
 === "Python"
@@ -96,4 +144,39 @@ Now we can invoke our graph to ensure it is working. Make sure to change the inp
     }
     ```
 
+  === "CURL"
+
+    ```bash
+    curl --request POST \
+     --url <DEPLOYMENT_URL>/threads/<THREAD_ID>/runs/stream \
+     --header 'Content-Type: application/json' \
+     --data "{
+       \"assistant_id\": \"agent\",
+       \"input\": {\"messages\": [{\"role\": \"human\", \"content\": \"what's the weather in sf\"}]},
+       \"stream_mode\": [
+         \"events\"
+       ]
+     }" | \
+     sed 's/\r$//' | \
+     awk '
+     /^event:/ {
+         if (data_content != "") {
+             print data_content "\n"
+         }
+         sub(/^event: /, "Receiving event of type: ", $0)
+         printf "%s...\n", $0
+         data_content = ""
+     }
+     /^data:/ {
+         sub(/^data: /, "", $0)
+         data_content = $0
+     }
+     END {
+         if (data_content != "") {
+             print data_content "\n"
+         }
+     }
+     ' 
+    ```
+
 If your graph works correctly, you should see your graph output displayed in the console. Of course, there are many more ways you might need to test your graph, for a full list of commands you can send with the SDK, see the [Python](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/python_sdk_ref/) and [JS/TS](https://langchain-ai.github.io/langgraph/cloud/reference/sdk/js_ts_sdk_ref/) references.

docs/docs/cloud/how-tos/check_thread_status.md

@@ -12,7 +12,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -22,7 +22,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = agent;
     const thread = await client.threads.create();
     ```
@@ -32,10 +32,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 ## Find idle threads

docs/docs/cloud/how-tos/enqueue_concurrent.md

@@ -31,7 +31,7 @@ Then, let's import our required packages and instantiate our client, assistant,
     from langchain_core.messages import convert_to_messages
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -42,7 +42,7 @@ Then, let's import our required packages and instantiate our client, assistant,
     import { Client } from "@langchain/langgraph-sdk";
     
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```

docs/docs/cloud/how-tos/human_in_the_loop_breakpoint.md

@@ -21,7 +21,7 @@ In this how-to we use a simple ReAct style hosted graph (you can see the full co
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -31,7 +31,7 @@ In this how-to we use a simple ReAct style hosted graph (you can see the full co
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent"
     const thread = await client.threads.create();
     ```
@@ -41,10 +41,7 @@ In this how-to we use a simple ReAct style hosted graph (you can see the full co
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 ## Adding a breakpoint

docs/docs/cloud/how-tos/human_in_the_loop_edit_state.md

@@ -17,7 +17,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -27,7 +27,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```
@@ -37,10 +37,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 ## Editing state

docs/docs/cloud/how-tos/human_in_the_loop_review_tool_calls.md

@@ -28,7 +28,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -38,7 +38,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```

docs/docs/cloud/how-tos/human_in_the_loop_time_travel.md

@@ -14,7 +14,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -24,7 +24,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = agent;
     const thread = await client.threads.create();
     ```
@@ -34,10 +34,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 ## Replay a state

docs/docs/cloud/how-tos/human_in_the_loop_user_input.md

@@ -24,7 +24,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
 
     ```python
     from langgraph_sdk import get_client
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -34,7 +34,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```
@@ -44,10 +44,7 @@ First, we need to setup our client so that we can communicate with our hosted gr
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 ## Waiting for user input

docs/docs/cloud/how-tos/interrupt_concurrent.md

@@ -29,7 +29,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     from langchain_core.messages import convert_to_messages
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -39,7 +39,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```

docs/docs/cloud/how-tos/reject_concurrent.md

@@ -28,7 +28,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     from langchain_core.messages import convert_to_messages
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -38,7 +38,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```

docs/docs/cloud/how-tos/rollback_concurrent.md

@@ -30,7 +30,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     from langchain_core.messages import convert_to_messages
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     assistant_id = "agent"
     thread = await client.threads.create()
     ```
@@ -40,7 +40,7 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     const assistantId = "agent";
     const thread = await client.threads.create();
     ```

docs/docs/cloud/how-tos/stream_debug.md

@@ -9,7 +9,7 @@ First let's set up our client and thread:
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -20,7 +20,7 @@ First let's set up our client and thread:
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)

docs/docs/cloud/how-tos/stream_events.md

@@ -6,7 +6,7 @@ This guide covers how to stream events from your graph (`stream_mode="events"`).
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -17,7 +17,7 @@ This guide covers how to stream events from your graph (`stream_mode="events"`).
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)
@@ -28,10 +28,7 @@ This guide covers how to stream events from your graph (`stream_mode="events"`).
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 Output:

docs/docs/cloud/how-tos/stream_messages.md

@@ -41,7 +41,7 @@ First let's set up our client and thread:
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -52,7 +52,7 @@ First let's set up our client and thread:
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)
@@ -63,10 +63,7 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 Output:

docs/docs/cloud/how-tos/stream_multiple.md

@@ -9,7 +9,7 @@ First let's set up our client and thread:
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -20,7 +20,7 @@ First let's set up our client and thread:
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)
@@ -31,10 +31,7 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 Output:

docs/docs/cloud/how-tos/stream_updates.md

@@ -16,7 +16,7 @@ First let's set up our client and thread:
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -27,7 +27,7 @@ First let's set up our client and thread:
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl:"<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)
@@ -38,10 +38,7 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 Output:

docs/docs/cloud/how-tos/stream_values.md

@@ -16,7 +16,7 @@ First let's set up our client and thread:
     ```python
     from langgraph_sdk import get_client
 
-    client = get_client(url="<DEPLOYMENT_URL>")
+    client = get_client(url=<DEPLOYMENT_URL>)
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -27,7 +27,7 @@ First let's set up our client and thread:
     ```js
     import { Client } from "@langchain/langgraph-sdk";
 
-    const client = new Client({ apiUrl: "<DEPLOYMENT_URL>" });
+    const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
     // create thread
     const thread = await client.threads.create();
     console.log(thread)
@@ -38,10 +38,7 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json' \
-      --data '{
-        "metadata": {}
-      }'
+      --header 'Content-Type: application/json'
     ```
 
 Output: