langchain-ai/langgraph
1
0
Fork 0
mirror of https://github.com/langchain-ai/langgraph.git synced 2026-07-15 12:35:43 -04:00
Code Issues 314 Packages Projects Releases 17 Wiki Activity

human in the loop #350

New Issue
Closed
opened 2026-02-20 17:38:01 -05:00 by yindo · 4 comments
yindo commented 2026-02-20 17:38:01 -05:00
Owner
Copy Link
Copy Source

Originally created by @nicho2 on GitHub (Dec 12, 2024).

Checked other resources

  • This is a bug, not a usage question. For questions, please use GitHub Discussions.
  • I added a clear and detailed title that summarizes the issue.
  • I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
  • I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

def human_review_node(state) -> Command[Literal["assistant", "sensitive_tools"]]:
    last_message = state["messages"][-1]
    tool_call = last_message.tool_calls[-1]

    # this is the value we'll be providing via Command(resume=<human_review>)
    human_review = interrupt(
        {
            "question": "Is this correct?",
            # Surface tool calls for review
            "tool_call": tool_call,
        }
    )

    review_action = human_review["action"]
    review_data = human_review.get("data")

    # if approved, call the tool
    if review_action == "continue":
        return Command(goto="sensitive_tools")

    # update the AI message AND call tools
    elif review_action == "update":
        updated_message = {
            "role": "ai",
            "content": last_message.content,
            "tool_calls": [
                {
                    "id": tool_call["id"],
                    "name": tool_call["name"],
                    # This the update provided by the human
                    "args": review_data,
                }
            ],
            # This is important - this needs to be the same as the message you replacing!
            # Otherwise, it will show up as a separate message
            "id": last_message.id,
        }
        return Command(goto="sensitive_tools", update={"messages": [updated_message]})

    # provide feedback to LLM
    elif review_action == "feedback":
        # NOTE: we're adding feedback message as a ToolMessage
        # to preserve the correct order in the message history
        # (AI messages with tool calls need to be followed by tool call messages)
        tool_message = {
            "role": "tool",
            # This is our natural language feedback
            "content": review_data,
            "name": tool_call["name"],
            "tool_call_id": tool_call["id"],
        }
        return Command(goto="assistant", update={"messages": [tool_message]})

Error Message and Stack Trace (if applicable)

human_review_node -> {'messages': [HumanMessage(content='je veux réserver le bureau alain de 12h à 13h', additional_kwargs={}, response_metadata={}, id='94a98107-f5cb-4ed8-b84e-2f43eea7a471'),
              AIMessage(content='', additional_kwargs={}, response_metadata={'model': 'llama3.3:latest', 'created_at': '2024-12-12T13:28:50.342536747Z', 'done': True, 'done_reason': 'stop', 'total_duration': 4300589516, 'load_duration': 19115485, 'prompt_eval_count': 1339, 'prompt_eval_duration': 1453000000, 'eval_count': 50, 'eval_duration': 2820000000, 'message': Message(role='assistant', content='', images=None, tool_calls=[ToolCall(function=Function(name='create_reservations', arguments={'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}))])}, id='run-2ebb4e90-2d72-4314-b9cf-be499c0793ab-0', tool_calls=[{'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}], usage_metadata={'input_tokens': 1339, 'output_tokens': 50, 'total_tokens': 1389})],
 'user_info': {'userId': 2, 'username': 'admin'}}
[chain/start] [chain:/chat > chain:human_review_node] Entering Chain run with input:
[inputs]
[chain/error] [chain:/chat > chain:human_review_node] [4ms] Chain run errored with error:
"GraphInterrupt((Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:45e45478-3673-4df5-ef4f-f2492bf5fdf5'], when='during'),))


Traceback (most recent call last):\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\utils\\runnable.py\", line 445, in ainvoke\n    input = await step.ainvoke(input, config, **kwargs)\n            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\utils\\runnable.py\", line 236, in ainvoke\n    ret = await asyncio.create_task(coro, context=context)\n          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langchain_core\\runnables\\config.py\", line 588, in run_in_executor\n    return await asyncio.get_running_loop().run_in_executor(\n           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n  File \"C:\\Python312\\Lib\\concurrent\\futures\\thread.py\", line 58, in run\n    result = self.fn(*self.args, **self.kwargs)\n             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langchain_core\\runnables\\config.py\", line 579, in wrapper\n    return func(*args, **kwargs)\n           ^^^^^^^^^^^^^^^^^^^^^\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\backend\\assistants\\assistant.py\", line 87, in human_review_node\n    human_review = interrupt(\n                   ^^^^^^^^^^\n\n\n  File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\types.py\", line 390, in interrupt\n    raise GraphInterrupt(\n\n\nlanggraph.errors.GraphInterrupt: (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:45e45478-3673-4df5-ef4f-f2492bf5fdf5'], when='during'),)"
[chain/end] [chain:/chat] [4.37s] Exiting Chain run with output:
[outputs]
2024-12-12 14:28:48,773 - langchain_core.callbacks.manager - WARNING - Error in LangChainTracer.on_chain_error callback: TracerException('No indexed run ID f0a5023c-2ff7-4c5e-99cf-447923f7236b.')
2024-12-12 14:28:48,774 - langchain_core.callbacks.manager - WARNING - Error in ConsoleCallbackHandler.on_chain_error callback: TracerException('No indexed run ID f0a5023c-2ff7-4c5e-99cf-447923f7236b.')

Description

i try to use human in the loop with langgraph but i have the error listed above.

my graph is :

%%{init: {'flowchart': {'curve': 'linear'}}}%%
graph TD;
	__start__([<p>__start__</p>]):::first
	fetch_user_info(fetch_user_info)
	assistant(assistant)
	safe_tools(safe_tools)
	human_review_node(human_review_node)
	sensitive_tools(sensitive_tools)
	__end__([<p>__end__</p>]):::last
	__start__ --> fetch_user_info;
	fetch_user_info --> assistant;
	safe_tools --> assistant;
	sensitive_tools --> assistant;
	assistant -.-> safe_tools;
	assistant -.-> human_review_node;
	assistant -.-> __end__;
	human_review_node -.-> assistant;
	human_review_node -.-> sensitive_tools;
	classDef default fill:#f2f0ff,line-height:1.2
	classDef first fill-opacity:0
	classDef last fill:#bfb6fc

System Info

System Information

OS: Windows
OS Version: 10.0.19045
Python Version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)]

Package Information

langchain_core: 0.3.24
langchain: 0.3.11
langchain_community: 0.3.11
langsmith: 0.2.3
langchain_ollama: 0.2.1
langchain_openai: 0.2.11
langchain_text_splitters: 0.3.2
langgraph_sdk: 0.1.43
langserve: 0.3.0

Other Dependencies

aiohttp: 3.11.10
async-timeout: Installed. No version info available.
dataclasses-json: 0.6.7
fastapi: 0.115.6
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 2.1.3
ollama: 0.4.2
openai: 1.57.0
orjson: 3.10.12
packaging: 24.2
pydantic: 2.10.3
pydantic-settings: 2.6.1
PyYAML: 6.0.2
requests: 2.32.3
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.36
sse-starlette: 2.1.3
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2

Originally created by @nicho2 on GitHub (Dec 12, 2024). ### Checked other resources - [X] This is a bug, not a usage question. For questions, please use GitHub Discussions. - [X] I added a clear and detailed title that summarizes the issue. - [X] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example). - [X] I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue. ### Example Code ```python def human_review_node(state) -> Command[Literal["assistant", "sensitive_tools"]]: last_message = state["messages"][-1] tool_call = last_message.tool_calls[-1] # this is the value we'll be providing via Command(resume=<human_review>) human_review = interrupt( { "question": "Is this correct?", # Surface tool calls for review "tool_call": tool_call, } ) review_action = human_review["action"] review_data = human_review.get("data") # if approved, call the tool if review_action == "continue": return Command(goto="sensitive_tools") # update the AI message AND call tools elif review_action == "update": updated_message = { "role": "ai", "content": last_message.content, "tool_calls": [ { "id": tool_call["id"], "name": tool_call["name"], # This the update provided by the human "args": review_data, } ], # This is important - this needs to be the same as the message you replacing! # Otherwise, it will show up as a separate message "id": last_message.id, } return Command(goto="sensitive_tools", update={"messages": [updated_message]}) # provide feedback to LLM elif review_action == "feedback": # NOTE: we're adding feedback message as a ToolMessage # to preserve the correct order in the message history # (AI messages with tool calls need to be followed by tool call messages) tool_message = { "role": "tool", # This is our natural language feedback "content": review_data, "name": tool_call["name"], "tool_call_id": tool_call["id"], } return Command(goto="assistant", update={"messages": [tool_message]}) ``` ### Error Message and Stack Trace (if applicable) ```shell human_review_node -> {'messages': [HumanMessage(content='je veux réserver le bureau alain de 12h à 13h', additional_kwargs={}, response_metadata={}, id='94a98107-f5cb-4ed8-b84e-2f43eea7a471'), AIMessage(content='', additional_kwargs={}, response_metadata={'model': 'llama3.3:latest', 'created_at': '2024-12-12T13:28:50.342536747Z', 'done': True, 'done_reason': 'stop', 'total_duration': 4300589516, 'load_duration': 19115485, 'prompt_eval_count': 1339, 'prompt_eval_duration': 1453000000, 'eval_count': 50, 'eval_duration': 2820000000, 'message': Message(role='assistant', content='', images=None, tool_calls=[ToolCall(function=Function(name='create_reservations', arguments={'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}))])}, id='run-2ebb4e90-2d72-4314-b9cf-be499c0793ab-0', tool_calls=[{'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}], usage_metadata={'input_tokens': 1339, 'output_tokens': 50, 'total_tokens': 1389})], 'user_info': {'userId': 2, 'username': 'admin'}} [chain/start] [chain:/chat > chain:human_review_node] Entering Chain run with input: [inputs] [chain/error] [chain:/chat > chain:human_review_node] [4ms] Chain run errored with error: "GraphInterrupt((Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:45e45478-3673-4df5-ef4f-f2492bf5fdf5'], when='during'),)) Traceback (most recent call last):\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\utils\\runnable.py\", line 445, in ainvoke\n input = await step.ainvoke(input, config, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\utils\\runnable.py\", line 236, in ainvoke\n ret = await asyncio.create_task(coro, context=context)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langchain_core\\runnables\\config.py\", line 588, in run_in_executor\n return await asyncio.get_running_loop().run_in_executor(\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"C:\\Python312\\Lib\\concurrent\\futures\\thread.py\", line 58, in run\n result = self.fn(*self.args, **self.kwargs)\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langchain_core\\runnables\\config.py\", line 579, in wrapper\n return func(*args, **kwargs)\n ^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\backend\\assistants\\assistant.py\", line 87, in human_review_node\n human_review = interrupt(\n ^^^^^^^^^^\n\n\n File \"C:\\Users\\suchaudn\\OneDrive - Legrand France\\PYTHON\\gimelec_agent\\.venv\\Lib\\site-packages\\langgraph\\types.py\", line 390, in interrupt\n raise GraphInterrupt(\n\n\nlanggraph.errors.GraphInterrupt: (Interrupt(value={'question': 'Is this correct?', 'tool_call': {'name': 'create_reservations', 'args': {'end_datetime_str': '2024-12-12T13:00:00', 'start_datetime_str': '2024-12-12T12:00:00'}, 'id': 'ae703317-b1b5-45aa-baed-9d8e942a244d', 'type': 'tool_call'}}, resumable=True, ns=['human_review_node:45e45478-3673-4df5-ef4f-f2492bf5fdf5'], when='during'),)" [chain/end] [chain:/chat] [4.37s] Exiting Chain run with output: [outputs] 2024-12-12 14:28:48,773 - langchain_core.callbacks.manager - WARNING - Error in LangChainTracer.on_chain_error callback: TracerException('No indexed run ID f0a5023c-2ff7-4c5e-99cf-447923f7236b.') 2024-12-12 14:28:48,774 - langchain_core.callbacks.manager - WARNING - Error in ConsoleCallbackHandler.on_chain_error callback: TracerException('No indexed run ID f0a5023c-2ff7-4c5e-99cf-447923f7236b.') ``` ### Description i try to use human in the loop with langgraph but i have the error listed above. my graph is : ```mermaid %%{init: {'flowchart': {'curve': 'linear'}}}%% graph TD; __start__([<p>__start__</p>]):::first fetch_user_info(fetch_user_info) assistant(assistant) safe_tools(safe_tools) human_review_node(human_review_node) sensitive_tools(sensitive_tools) __end__([<p>__end__</p>]):::last __start__ --> fetch_user_info; fetch_user_info --> assistant; safe_tools --> assistant; sensitive_tools --> assistant; assistant -.-> safe_tools; assistant -.-> human_review_node; assistant -.-> __end__; human_review_node -.-> assistant; human_review_node -.-> sensitive_tools; classDef default fill:#f2f0ff,line-height:1.2 classDef first fill-opacity:0 classDef last fill:#bfb6fc ``` ### System Info System Information ------------------ > OS: Windows > OS Version: 10.0.19045 > Python Version: 3.12.7 (tags/v3.12.7:0b05ead, Oct 1 2024, 03:06:41) [MSC v.1941 64 bit (AMD64)] Package Information ------------------- > langchain_core: 0.3.24 > langchain: 0.3.11 > langchain_community: 0.3.11 > langsmith: 0.2.3 > langchain_ollama: 0.2.1 > langchain_openai: 0.2.11 > langchain_text_splitters: 0.3.2 > langgraph_sdk: 0.1.43 > langserve: 0.3.0 Other Dependencies ------------------ > aiohttp: 3.11.10 > async-timeout: Installed. No version info available. > dataclasses-json: 0.6.7 > fastapi: 0.115.6 > httpx: 0.27.2 > httpx-sse: 0.4.0 > jsonpatch: 1.33 > langsmith-pyo3: Installed. No version info available. > numpy: 2.1.3 > ollama: 0.4.2 > openai: 1.57.0 > orjson: 3.10.12 > packaging: 24.2 > pydantic: 2.10.3 > pydantic-settings: 2.6.1 > PyYAML: 6.0.2 > requests: 2.32.3 > requests-toolbelt: 1.0.0 > SQLAlchemy: 2.0.36 > sse-starlette: 2.1.3 > tenacity: 9.0.0 > tiktoken: 0.8.0 > typing-extensions: 4.12.2
yindo closed this issue 2026-02-20 17:38:01 -05:00
yindo commented 2026-02-20 17:38:01 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Dec 12, 2024):

@nicho2 can you provide a code snippet with the full graph and how you're invoking it? (ie minimal reproducible example)

@vbarda commented on GitHub (Dec 12, 2024): @nicho2 can you provide a code snippet with the full graph and how you're invoking it? (ie minimal reproducible example)
yindo commented 2026-02-20 17:38:01 -05:00
Author
Owner
Copy Link
Copy Source

@nicho2 commented on GitHub (Dec 12, 2024):

def create_graph() -> CompiledGraph:

memory = MemorySaver()      # memorisation en Ram, mais on peut utiliser un sqllite ou postgres

builder = StateGraph(State,ConfigurableForGraph)

# NEW: The fetch_user_info node runs first, meaning our assistant can see the user's flight information without
# having to take an action
builder.add_node("fetch_user_info", user_info)
builder.add_edge(START, "fetch_user_info")
assistant_runnable,safe_tools,sensitive_tools = create_chain()
builder.add_node("assistant", Assistant(assistant_runnable))
builder.add_node("safe_tools", create_tool_node_with_fallback(safe_tools))
builder.add_node(human_review_node)
builder.add_node(
    "sensitive_tools", create_tool_node_with_fallback(sensitive_tools)
)
builder.add_edge("fetch_user_info", "assistant")

builder.add_conditional_edges(
    "assistant",
    route_tools,
    ["safe_tools", "human_review_node", END]
)
builder.add_edge("safe_tools", "assistant")
builder.add_edge("sensitive_tools", "assistant")

graph = builder.compile(
    checkpointer=memory,
    # NEW: The graph will always halt before executing the "tools" node.
    # The user can approve or reject (or even alter the request) before
    # the assistant continues
    #interrupt_before=["sensitive_tools"],
    debug=True
)
print(graph.get_graph().draw_mermaid())
return graph
@nicho2 commented on GitHub (Dec 12, 2024): def create_graph() -> CompiledGraph: memory = MemorySaver() # memorisation en Ram, mais on peut utiliser un sqllite ou postgres builder = StateGraph(State,ConfigurableForGraph) # NEW: The fetch_user_info node runs first, meaning our assistant can see the user's flight information without # having to take an action builder.add_node("fetch_user_info", user_info) builder.add_edge(START, "fetch_user_info") assistant_runnable,safe_tools,sensitive_tools = create_chain() builder.add_node("assistant", Assistant(assistant_runnable)) builder.add_node("safe_tools", create_tool_node_with_fallback(safe_tools)) builder.add_node(human_review_node) builder.add_node( "sensitive_tools", create_tool_node_with_fallback(sensitive_tools) ) builder.add_edge("fetch_user_info", "assistant") builder.add_conditional_edges( "assistant", route_tools, ["safe_tools", "human_review_node", END] ) builder.add_edge("safe_tools", "assistant") builder.add_edge("sensitive_tools", "assistant") graph = builder.compile( checkpointer=memory, # NEW: The graph will always halt before executing the "tools" node. # The user can approve or reject (or even alter the request) before # the assistant continues #interrupt_before=["sensitive_tools"], debug=True ) print(graph.get_graph().draw_mermaid()) return graph
yindo commented 2026-02-20 17:38:01 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Dec 12, 2024):

@nicho2 thanks, but could you actually expand it with the actual node implementations (could be some fake code as long as it reproduces the actual issue) https://stackoverflow.com/help/minimal-reproducible-example

@vbarda commented on GitHub (Dec 12, 2024): @nicho2 thanks, but could you actually expand it with the actual node implementations (could be some fake code as long as it reproduces the actual issue) https://stackoverflow.com/help/minimal-reproducible-example
yindo commented 2026-02-20 17:38:02 -05:00
Author
Owner
Copy Link
Copy Source

@vbarda commented on GitHub (Dec 20, 2024):

Going to close this issue, but feel free to reopen/make a new issue with a minimal reproducible example

@vbarda commented on GitHub (Dec 20, 2024): Going to close this issue, but feel free to reopen/make a new issue with a minimal reproducible example
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
agents
awaiting author revision
bug
change
chat models
checkpointer
ci
code quality
code quality
dependencies
documentation
drawing
duplicate
enhancement
good first issue
help wanted
invalid
maintainer
meta
missing information
not maintained by langchain
open-swe-auto
open-swe-max
open-swe-max-auto
pending
performance
pull-request
Mirrored from GitHub Pull Request
 question
requires design
sdk
server
stale
studio
tests
type checking
usage question
v0.5
v1.1
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/langgraph#350
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?