small fixes (#1629)

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

@@ -36,7 +36,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:

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

@@ -34,7 +34,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Find idle threads

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

@@ -78,7 +78,8 @@ Then, let's import our required packages and instantiate our client, assistant,
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Now let's start two runs, with the second interrupting the first one with a multitask strategy of "enqueue":

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

@@ -43,7 +43,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Adding a breakpoint

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

@@ -39,7 +39,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Editing state

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

@@ -50,7 +50,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Example with no review
@@ -177,7 +178,7 @@ Let's now look at what it looks like to approve a tool call. Note that we don't
 
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=input,
     ):
         if chunk.data and chunk.event != "metadata": 
@@ -278,7 +279,7 @@ To approve the tool call, we can just continue the thread with no edits. To do t
     ```python
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=None,
         stream_mode="values",
     ):
@@ -352,7 +353,7 @@ Let's now say we want to edit the tool call. E.g. change some of the parameters
 
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=input,
         stream_mode="values",
     ):
@@ -465,7 +466,7 @@ To do this, we first need to update the state. We can do this by passing a messa
     # Let's now continue executing from here
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=None,
     ):
         if chunk.data and chunk.event != "metadata": 
@@ -608,7 +609,7 @@ For this example we will just add a single tool call representing the feedback.
 
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=input,
     ):
         if chunk.data and chunk.event != "metadata": 
@@ -708,7 +709,7 @@ To do this, we first need to update the state. We can do this by passing a messa
     # Let's now continue executing from here
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=None,
         stream_mode="values",
     ):
@@ -827,7 +828,7 @@ We can see that we now get to another breakpoint - because it went back to the m
     ```python
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=None,
     ):
         if chunk.data and chunk.event != "metadata": 

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

@@ -36,7 +36,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Replay a state

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

@@ -46,7 +46,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 ## Waiting for user input

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

@@ -75,7 +75,8 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Now we can start our two runs and join the second on euntil it has completed:

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

@@ -74,7 +74,8 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Now we can run a thread and try to run a second one with the "reject" option, which should fail since we have already started a run:

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

@@ -76,7 +76,8 @@ Now, let's import our required packages and instantiate our client, assistant, a
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Now let's run a thread with the multitask parameter set to "rollback":

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

@@ -39,7 +39,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 

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

@@ -33,7 +33,8 @@ 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'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:

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

@@ -71,7 +71,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:

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

@@ -35,7 +35,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:

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

@@ -10,6 +10,8 @@ First let's set up our client and thread:
     from langgraph_sdk import get_client
 
     client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -21,6 +23,8 @@ First let's set up our client and thread:
     import { Client } from "@langchain/langgraph-sdk";
 
     const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
     // create thread
     const thread = await client.threads.create();
     console.log(thread);
@@ -31,7 +35,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:
@@ -62,7 +67,7 @@ Now we can stream by updates, which outputs updates made to the state by each no
     }
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=input,
         stream_mode="updates",
     ):
@@ -85,7 +90,7 @@ Now we can stream by updates, which outputs updates made to the state by each no
 
     const streamResponse = client.runs.stream(
       thread["thread_id"],
-      "agent",
+      assistantID,
       {
         input,
         streamMode: "updates"

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

@@ -10,6 +10,8 @@ First let's set up our client and thread:
     from langgraph_sdk import get_client
 
     client = get_client(url=<DEPLOYMENT_URL>)
+    # Using the graph deployed with the name "agent"
+    assistant_id = "agent"
     # create thread
     thread = await client.threads.create()
     print(thread)
@@ -21,6 +23,8 @@ First let's set up our client and thread:
     import { Client } from "@langchain/langgraph-sdk";
 
     const client = new Client({ apiUrl: <DEPLOYMENT_URL> });
+    // Using the graph deployed with the name "agent"
+    const assistantID = "agent";
     // create thread
     const thread = await client.threads.create();
     console.log(thread);
@@ -31,7 +35,8 @@ First let's set up our client and thread:
     ```bash
     curl --request POST \
       --url <DEPLOYMENT_URL>/threads \
-      --header 'Content-Type: application/json'
+      --header 'Content-Type: application/json' \
+      --data '{}'
     ```
 
 Output:
@@ -56,7 +61,7 @@ Now we can stream by values, which streams the full state of the graph after eac
     # stream values
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent", 
+        assistant_id, 
         input=input,
         stream_mode="values"
     ):
@@ -72,7 +77,7 @@ Now we can stream by values, which streams the full state of the graph after eac
 
     const streamResponse = client.runs.stream(
       thread["thread_id"],
-      "agent",
+      assistantID,
       {
         input,
         streamMode: "values"
@@ -164,7 +169,7 @@ If we want to just get the final result, we can use this endpoint and just keep
     final_answer = None
     async for chunk in client.runs.stream(
         thread["thread_id"],
-        "agent",
+        assistant_id,
         input=input,
         stream_mode="values"
     ):
@@ -178,7 +183,7 @@ If we want to just get the final result, we can use this endpoint and just keep
     let finalAnswer;
     const streamResponse = client.runs.stream(
       thread["thread_id"],
-      "agent",
+      assistantID,
       {
         input,
         streamMode: "values"