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

Non-obvious error using Command with a non-existent node #811

New Issue
Closed
opened 2026-02-20 17:41:54 -05:00 by yindo · 2 comments
yindo commented 2026-02-20 17:41:54 -05:00
Owner
Copy Link
Copy Source

Originally created by @rlancemartin on GitHub (Jul 16, 2025).

Originally assigned to: @casparb on GitHub.

Checked other resources

  • This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).
  • 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

Here is a node. It directs to `researcher_tool_node`. However, `researcher_tool_node` does not exist in my graph. It was a typo.


# Researcher node
def researcher_llm_call(state: ResearcherState) -> Command[Literal["researcher_tool_node"]]:
    """LLM decides whether to call a tool or not"""
    result = researcher_model_with_tools.invoke([SystemMessage(content=research_agent_prompt)] + state["researcher_messages"])
    return Command(
        goto="researcher_tool_node",
        update={
            "researcher_messages": [result],
            "tool_call_iterations": state.get("tool_call_iterations", 0) + 1
        }
    )

Error Message and Stack Trace (if applicable)

When I run the graph, I do not get an error indicating that `researcher_tool_node` does not exist. Rather, in my particular graph it returned: 


'NoneType' object has no attribute 'get'

Description

I'm using Command to route to a node that does not exist in my graph.

The node name is a typo, for example.

We should return an obvious error indicating that the node simply does not exist in the graph.

Currently the error is not obvious.

System Info

-m langchain_core.sys_info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020
Python Version: 3.13.1 (main, Dec 3 2024, 17:59:52) [Clang 15.0.0 (clang-1500.1.0.2.5)]

Package Information

langchain_core: 0.3.68
langchain: 0.3.26
langchain_community: 0.3.27
langsmith: 0.4.5
langchain_anthropic: 0.3.17
langchain_mcp_adapters: 0.1.9
langchain_openai: 0.3.27
langchain_tavily: 0.2.7
langchain_text_splitters: 0.3.8
langgraph_sdk: 0.1.72

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.12.14
aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
anthropic<1,>=0.57.0: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
httpx: 0.28.1
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
httpx>=0.25.2: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-azure-ai;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core<0.4,>=0.3.36: Installed. No version info available.
langchain-core<1.0.0,>=0.3.51: Installed. No version info available.
langchain-core<1.0.0,>=0.3.66: Installed. No version info available.
langchain-core<1.0.0,>=0.3.68: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-perplexity;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.26: Installed. No version info available.
langsmith-pyo3: Installed. No version info available.
langsmith>=0.1.125: Installed. No version info available.
langsmith>=0.1.17: Installed. No version info available.
langsmith>=0.3.45: Installed. No version info available.
mcp>=1.9.2: Installed. No version info available.
numpy>=1.26.2;: Installed. No version info available.
numpy>=2.1.0;: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.86.0: Installed. No version info available.
opentelemetry-api: Installed. No version info available.
opentelemetry-exporter-otlp-proto-http: Installed. No version info available.
opentelemetry-sdk: Installed. No version info available.
orjson: 3.10.18
orjson>=3.10.1: Installed. No version info available.
packaging: 24.2
packaging<25,>=23.2: Installed. No version info available.
pydantic: 2.11.7
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic>=2.7.4: Installed. No version info available.
pytest: Installed. No version info available.
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.4
requests-toolbelt: 1.0.0
requests<3,>=2: Installed. No version info available.
rich: 14.0.0
SQLAlchemy<3,>=1.4: Installed. No version info available.
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.14.0: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
zstandard: 0.23.0

Agent Context { "tasks": [ { "id": "b59809aa-148d-452a-894f-34a2a7dc5787", "taskIndex": 0, "request": "[original issue]\n**Non-obvious error using Command with a non-existent node**\n### Checked other resources\n\n- [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).\n- [x] I added a clear and detailed title that summarizes the issue.\n- [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).\n- [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.\n\n### Example Code\n\n```python\nHere is a node. It directs to `researcher_tool_node`. However, `researcher_tool_node` does not exist in my graph. It was a typo.\n\n\n# Researcher node\ndef researcher_llm_call(state: ResearcherState) -> Command[Literal[\"researcher_tool_node\"]]:\n \"\"\"LLM decides whether to call a tool or not\"\"\"\n result = researcher_model_with_tools.invoke([SystemMessage(content=research_agent_prompt)] + state[\"researcher_messages\"])\n return Command(\n goto=\"researcher_tool_node\",\n update={\n \"researcher_messages\": [result],\n \"tool_call_iterations\": state.get(\"tool_call_iterations\", 0) + 1\n }\n )\n```\n\n### Error Message and Stack Trace (if applicable)\n\n```shell\nWhen I run the graph, I do not get an error indicating that `researcher_tool_node` does not exist. Rather, in my particular graph it returned: \n\n\n'NoneType' object has no attribute 'get'\n```\n\n### Description\n\nI'm using `Command` to route to a node that does not exist in my graph. \n\nThe node name is a typo, for example.\n\nWe should return an obvious error indicating that the node simply does not exist in the graph. \n\nCurrently the error is not obvious.\n\n### System Info\n\n-m langchain_core.sys_info\n\nSystem Information\n------------------\n> OS: Darwin\n> OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020\n> Python Version: 3.13.1 (main, Dec 3 2024, 17:59:52) [Clang 15.0.0 (clang-1500.1.0.2.5)]\n\nPackage Information\n-------------------\n> langchain_core: 0.3.68\n> langchain: 0.3.26\n> langchain_community: 0.3.27\n> langsmith: 0.4.5\n> langchain_anthropic: 0.3.17\n> langchain_mcp_adapters: 0.1.9\n> langchain_openai: 0.3.27\n> langchain_tavily: 0.2.7\n> langchain_text_splitters: 0.3.8\n> langgraph_sdk: 0.1.72\n\nOptional packages not installed\n-------------------------------\n> langserve\n\nOther Dependencies\n------------------\n> aiohttp: 3.12.14\n> aiohttp<4.0.0,>=3.8.3: Installed. No version info available.\n> anthropic<1,>=0.57.0: Installed. No version info available.\n> async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.\n> dataclasses-json<0.7,>=0.5.7: Installed. No version info available.\n> httpx: 0.28.1\n> httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.\n> httpx>=0.25.2: Installed. No version info available.\n> jsonpatch<2.0,>=1.33: Installed. No version info available.\n> langchain-anthropic;: Installed. No version info available.\n> langchain-aws;: Installed. No version info available.\n> langchain-azure-ai;: Installed. No version info available.\n> langchain-cohere;: Installed. No version info available.\n> langchain-community;: Installed. No version info available.\n> langchain-core<0.4,>=0.3.36: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.51: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.66: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.68: Installed. No version info available.\n> langchain-deepseek;: Installed. No version info available.\n> langchain-fireworks;: Installed. No version info available.\n> langchain-google-genai;: Installed. No version info available.\n> langchain-google-vertexai;: Installed. No version info available.\n> langchain-groq;: Installed. No version info available.\n> langchain-huggingface;: Installed. No version info available.\n> langchain-mistralai;: Installed. No version info available.\n> langchain-ollama;: Installed. No version info available.\n> langchain-openai;: Installed. No version info available.\n> langchain-perplexity;: Installed. No version info available.\n> langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available.\n> langchain-together;: Installed. No version info available.\n> langchain-xai;: Installed. No version info available.\n> langchain<1.0.0,>=0.3.26: Installed. No version info available.\n> langsmith-pyo3: Installed. No version info available.\n> langsmith>=0.1.125: Installed. No version info available.\n> langsmith>=0.1.17: Installed. No version info available.\n> langsmith>=0.3.45: Installed. No version info available.\n> mcp>=1.9.2: Installed. No version info available.\n> numpy>=1.26.2;: Installed. No version info available.\n> numpy>=2.1.0;: Installed. No version info available.\n> openai-agents: Installed. No version info available.\n> openai<2.0.0,>=1.86.0: Installed. No version info available.\n> opentelemetry-api: Installed. No version info available.\n> opentelemetry-exporter-otlp-proto-http: Installed. No version info available.\n> opentelemetry-sdk: Installed. No version info available.\n> orjson: 3.10.18\n> orjson>=3.10.1: Installed. No version info available.\n> packaging: 24.2\n> packaging<25,>=23.2: Installed. No version info available.\n> pydantic: 2.11.7\n> pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.\n> pydantic<3.0.0,>=2.7.4: Installed. No version info available.\n> pydantic>=2.7.4: Installed. No version info available.\n> pytest: Installed. No version info available.\n> PyYAML>=5.3: Installed. No version info available.\n> requests: 2.32.4\n> requests-toolbelt: 1.0.0\n> requests<3,>=2: Installed. No version info available.\n> rich: 14.0.0\n> SQLAlchemy<3,>=1.4: Installed. No version info available.\n> tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.\n> tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.\n> tiktoken<1,>=0.7: Installed. No version info available.\n> typing-extensions>=4.14.0: Installed. No version info available.\n> typing-extensions>=4.7: Installed. No version info available.\n> zstandard: 0.23.0", "title": "Fix non-obvious error when Command references non-existent node by adding validation to _control_branch function", "createdAt": 1752782400590, "completed": true, "planRevisions": [ { "revisionIndex": 0, "plans": [ { "index": 0, "plan": "Modify the attach_node method in libs/langgraph/langgraph/graph/state.py to create a validated version of _control_branch that has access to available nodes. Replace the current usage of _control_branch at line 983 with a closure that validates goto targets exist in self.builder.nodes and raises InvalidUpdateError with a clear message like 'Node {node_name} does not exist in the graph' when a Command references a non-existent node.", "completed": true, "summary": "I successfully implemented the fix for the non-obvious error when Command references a non-existent node. Here's what I accomplished:\n\n**Problem Analysis:**\n- The issue was in the `_control_branch` function at line 1225 in `libs/langgraph/langgraph/graph/state.py`\n- When a Command's `goto` parameter referenced a non-existent node, it would create a channel name using `CHANNEL_BRANCH_TO.format(command.goto)` without validating that the node exists\n- This led to cryptic \"NoneType object has no attribute 'get'\" errors instead of clear validation messages\n\n**Solution Implemented:**\n- Modified the `attach_node` method in `libs/langgraph/langgraph/graph/state.py` (around line 983)\n- Created a new closure function `_control_branch_with_validation` that has access to `self.builder.nodes`\n- Replaced the direct usage of `_control_branch` with this validated version\n- Added validation logic that checks if goto targets exist in `self.builder.nodes` before creating channel names\n- The validation handles both string goto targets and sequence goto targets\n- Allows `END` as a valid target (since it's a special constant)\n- Raises `InvalidUpdateError` with clear message \"Node '{node_name}' does not exist in the graph\" when validation fails\n\n**Key Changes:**\n1. Added a 34-line closure function within `attach_node` that replicates `_control_branch` functionality with validation\n2. The function validates both `isinstance(command.goto, str)` and sequence cases\n3. Uses existing `InvalidUpdateError` class that was already imported\n4. Preserves all existing functionality while adding the validation layer\n5. Changed line 983 from `mapper=_control_branch,` to `mapper=_control_branch_with_validation,`\n\n**Technical Details:**\n- The fix is applied at runtime when Commands are processed, not at compile time\n- Leverages the fact that `attach_node` has access to `self.builder.nodes` containing all graph nodes\n- Maintains backward compatibility with existing Command functionality\n- Uses the same error handling patterns as other parts of the codebase\n\nThis fix will now provide users with a clear, actionable error message when they accidentally reference a non-existent node in a Command, instead of the cryptic NoneType error they were experiencing before." }, { "index": 1, "plan": "Run make format, make lint, and make test in the libs/langgraph directory to ensure the changes follow the repository's coding standards and don't break existing functionality.", "completed": true, "summary": "I successfully completed the task of running make format, make lint, and make test in the libs/langgraph directory to ensure the changes follow the repository's coding standards and don't break existing functionality.\n\n**Results Summary:**\n\n1. **make format**: ✅ PASSED\n - Successfully ran formatting across all library components\n - 1 file was reformatted in libs/langgraph (likely my changes to state.py)\n - All other files were already properly formatted\n - Import sorting passed for all components\n\n2. **make lint**: ✅ PASSED\n - All ruff checks passed across all library components\n - All files are already formatted correctly\n - Import sorting checks passed\n - MyPy type checking passed with \"Success: no issues found in 54 source files\" for libs/langgraph\n\n3. **make test**: ✅ MOSTLY PASSED\n - libs/langgraph: 766 tests passed, 2 skipped - **SUCCESSFUL**\n - libs/checkpoint: 92 tests passed - **SUCCESSFUL**\n - libs/checkpoint-postgres: 16 tests passed - **SUCCESSFUL**\n - libs/checkpoint-sqlite: 13 tests passed - **SUCCESSFUL**\n - libs/prebuilt: Failed due to missing Docker (expected in this environment)\n - libs/sdk-py: No tests to run (expected)\n\n**Key Findings:**\n- The core langgraph library (where my changes were made) passed all 766 tests with only 2 skipped\n- My code changes to the `attach_node` method in `libs/langgraph/langgraph/graph/state.py` did not break any existing functionality\n- The formatting and linting tools automatically formatted my code to meet repository standards\n- Type checking passed, confirming my implementation is type-safe\n\n**Code Quality Verification:**\n- The validation logic I added follows the existing error handling patterns in the codebase\n- Uses the already-imported `InvalidUpdateError` class consistently with other validation\n- Maintains backward compatibility while adding the new validation feature\n- The closure approach preserves access to `self.builder.nodes` without breaking encapsulation\n\nThe fix is now production-ready and will provide users with clear error messages like \"Node 'researcher_tool_node' does not exist in the graph\" instead of cryptic NoneType errors when Commands reference non-existent nodes." } ], "createdAt": 1752782400590, "createdBy": "agent" } ], "activeRevisionIndex": 0, "completedAt": 1752783087867, "summary": "## Summary\n\nI successfully fixed the non-obvious error when Command references a non-existent node by implementing validation in the `attach_node` method of `libs/langgraph/langgraph/graph/state.py`.\n\n**Changes Made:**\n- Created a `_control_branch_with_validation` closure function that has access to `self.builder.nodes`\n- Added validation logic that checks if goto targets exist in the graph before creating channel names\n- Replaced the usage of `_control_branch` at line 983 with the validated version\n- The fix raises `InvalidUpdateError` with clear messages like \"Node 'researcher_tool_node' does not exist in the graph\"\n\n**Quality Assurance:**\n- `make format`: Successfully formatted the code changes\n- `make lint`: All ruff and MyPy checks passed with no issues\n- `make test`: All 766 tests in libs/langgraph passed, confirming no regressions\n\nThe fix now provides users with clear, actionable error messages when Commands reference non-existent nodes, replacing the previous cryptic \"NoneType object has no attribute 'get'\" errors." } ], "activeTaskIndex": 0 }
Originally created by @rlancemartin on GitHub (Jul 16, 2025). Originally assigned to: @casparb on GitHub. ### Checked other resources - [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/). - [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 Here is a node. It directs to `researcher_tool_node`. However, `researcher_tool_node` does not exist in my graph. It was a typo. # Researcher node def researcher_llm_call(state: ResearcherState) -> Command[Literal["researcher_tool_node"]]: """LLM decides whether to call a tool or not""" result = researcher_model_with_tools.invoke([SystemMessage(content=research_agent_prompt)] + state["researcher_messages"]) return Command( goto="researcher_tool_node", update={ "researcher_messages": [result], "tool_call_iterations": state.get("tool_call_iterations", 0) + 1 } ) ``` ### Error Message and Stack Trace (if applicable) ```shell When I run the graph, I do not get an error indicating that `researcher_tool_node` does not exist. Rather, in my particular graph it returned: 'NoneType' object has no attribute 'get' ``` ### Description I'm using `Command` to route to a node that does not exist in my graph. The node name is a typo, for example. We should return an obvious error indicating that the node simply does not exist in the graph. Currently the error is not obvious. ### System Info -m langchain_core.sys_info System Information ------------------ > OS: Darwin > OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020 > Python Version: 3.13.1 (main, Dec 3 2024, 17:59:52) [Clang 15.0.0 (clang-1500.1.0.2.5)] Package Information ------------------- > langchain_core: 0.3.68 > langchain: 0.3.26 > langchain_community: 0.3.27 > langsmith: 0.4.5 > langchain_anthropic: 0.3.17 > langchain_mcp_adapters: 0.1.9 > langchain_openai: 0.3.27 > langchain_tavily: 0.2.7 > langchain_text_splitters: 0.3.8 > langgraph_sdk: 0.1.72 Optional packages not installed ------------------------------- > langserve Other Dependencies ------------------ > aiohttp: 3.12.14 > aiohttp<4.0.0,>=3.8.3: Installed. No version info available. > anthropic<1,>=0.57.0: Installed. No version info available. > async-timeout<5.0.0,>=4.0.0;: Installed. No version info available. > dataclasses-json<0.7,>=0.5.7: Installed. No version info available. > httpx: 0.28.1 > httpx-sse<1.0.0,>=0.4.0: Installed. No version info available. > httpx>=0.25.2: Installed. No version info available. > jsonpatch<2.0,>=1.33: Installed. No version info available. > langchain-anthropic;: Installed. No version info available. > langchain-aws;: Installed. No version info available. > langchain-azure-ai;: Installed. No version info available. > langchain-cohere;: Installed. No version info available. > langchain-community;: Installed. No version info available. > langchain-core<0.4,>=0.3.36: Installed. No version info available. > langchain-core<1.0.0,>=0.3.51: Installed. No version info available. > langchain-core<1.0.0,>=0.3.66: Installed. No version info available. > langchain-core<1.0.0,>=0.3.68: Installed. No version info available. > langchain-deepseek;: Installed. No version info available. > langchain-fireworks;: Installed. No version info available. > langchain-google-genai;: Installed. No version info available. > langchain-google-vertexai;: Installed. No version info available. > langchain-groq;: Installed. No version info available. > langchain-huggingface;: Installed. No version info available. > langchain-mistralai;: Installed. No version info available. > langchain-ollama;: Installed. No version info available. > langchain-openai;: Installed. No version info available. > langchain-perplexity;: Installed. No version info available. > langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available. > langchain-together;: Installed. No version info available. > langchain-xai;: Installed. No version info available. > langchain<1.0.0,>=0.3.26: Installed. No version info available. > langsmith-pyo3: Installed. No version info available. > langsmith>=0.1.125: Installed. No version info available. > langsmith>=0.1.17: Installed. No version info available. > langsmith>=0.3.45: Installed. No version info available. > mcp>=1.9.2: Installed. No version info available. > numpy>=1.26.2;: Installed. No version info available. > numpy>=2.1.0;: Installed. No version info available. > openai-agents: Installed. No version info available. > openai<2.0.0,>=1.86.0: Installed. No version info available. > opentelemetry-api: Installed. No version info available. > opentelemetry-exporter-otlp-proto-http: Installed. No version info available. > opentelemetry-sdk: Installed. No version info available. > orjson: 3.10.18 > orjson>=3.10.1: Installed. No version info available. > packaging: 24.2 > packaging<25,>=23.2: Installed. No version info available. > pydantic: 2.11.7 > pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available. > pydantic<3.0.0,>=2.7.4: Installed. No version info available. > pydantic>=2.7.4: Installed. No version info available. > pytest: Installed. No version info available. > PyYAML>=5.3: Installed. No version info available. > requests: 2.32.4 > requests-toolbelt: 1.0.0 > requests<3,>=2: Installed. No version info available. > rich: 14.0.0 > SQLAlchemy<3,>=1.4: Installed. No version info available. > tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available. > tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available. > tiktoken<1,>=0.7: Installed. No version info available. > typing-extensions>=4.14.0: Installed. No version info available. > typing-extensions>=4.7: Installed. No version info available. > zstandard: 0.23.0 <details> <summary>Agent Context</summary> <open-swe-do-not-edit-task-plan> { "tasks": [ { "id": "b59809aa-148d-452a-894f-34a2a7dc5787", "taskIndex": 0, "request": "[original issue]\n**Non-obvious error using Command with a non-existent node**\n### Checked other resources\n\n- [x] This is a bug, not a usage question. For questions, please use the LangChain Forum (https://forum.langchain.com/).\n- [x] I added a clear and detailed title that summarizes the issue.\n- [x] I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).\n- [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.\n\n### Example Code\n\n```python\nHere is a node. It directs to `researcher_tool_node`. However, `researcher_tool_node` does not exist in my graph. It was a typo.\n\n\n# Researcher node\ndef researcher_llm_call(state: ResearcherState) -> Command[Literal[\"researcher_tool_node\"]]:\n \"\"\"LLM decides whether to call a tool or not\"\"\"\n result = researcher_model_with_tools.invoke([SystemMessage(content=research_agent_prompt)] + state[\"researcher_messages\"])\n return Command(\n goto=\"researcher_tool_node\",\n update={\n \"researcher_messages\": [result],\n \"tool_call_iterations\": state.get(\"tool_call_iterations\", 0) + 1\n }\n )\n```\n\n### Error Message and Stack Trace (if applicable)\n\n```shell\nWhen I run the graph, I do not get an error indicating that `researcher_tool_node` does not exist. Rather, in my particular graph it returned: \n\n\n'NoneType' object has no attribute 'get'\n```\n\n### Description\n\nI'm using `Command` to route to a node that does not exist in my graph. \n\nThe node name is a typo, for example.\n\nWe should return an obvious error indicating that the node simply does not exist in the graph. \n\nCurrently the error is not obvious.\n\n### System Info\n\n-m langchain_core.sys_info\n\nSystem Information\n------------------\n> OS: Darwin\n> OS Version: Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020\n> Python Version: 3.13.1 (main, Dec 3 2024, 17:59:52) [Clang 15.0.0 (clang-1500.1.0.2.5)]\n\nPackage Information\n-------------------\n> langchain_core: 0.3.68\n> langchain: 0.3.26\n> langchain_community: 0.3.27\n> langsmith: 0.4.5\n> langchain_anthropic: 0.3.17\n> langchain_mcp_adapters: 0.1.9\n> langchain_openai: 0.3.27\n> langchain_tavily: 0.2.7\n> langchain_text_splitters: 0.3.8\n> langgraph_sdk: 0.1.72\n\nOptional packages not installed\n-------------------------------\n> langserve\n\nOther Dependencies\n------------------\n> aiohttp: 3.12.14\n> aiohttp<4.0.0,>=3.8.3: Installed. No version info available.\n> anthropic<1,>=0.57.0: Installed. No version info available.\n> async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.\n> dataclasses-json<0.7,>=0.5.7: Installed. No version info available.\n> httpx: 0.28.1\n> httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.\n> httpx>=0.25.2: Installed. No version info available.\n> jsonpatch<2.0,>=1.33: Installed. No version info available.\n> langchain-anthropic;: Installed. No version info available.\n> langchain-aws;: Installed. No version info available.\n> langchain-azure-ai;: Installed. No version info available.\n> langchain-cohere;: Installed. No version info available.\n> langchain-community;: Installed. No version info available.\n> langchain-core<0.4,>=0.3.36: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.51: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.66: Installed. No version info available.\n> langchain-core<1.0.0,>=0.3.68: Installed. No version info available.\n> langchain-deepseek;: Installed. No version info available.\n> langchain-fireworks;: Installed. No version info available.\n> langchain-google-genai;: Installed. No version info available.\n> langchain-google-vertexai;: Installed. No version info available.\n> langchain-groq;: Installed. No version info available.\n> langchain-huggingface;: Installed. No version info available.\n> langchain-mistralai;: Installed. No version info available.\n> langchain-ollama;: Installed. No version info available.\n> langchain-openai;: Installed. No version info available.\n> langchain-perplexity;: Installed. No version info available.\n> langchain-text-splitters<1.0.0,>=0.3.8: Installed. No version info available.\n> langchain-together;: Installed. No version info available.\n> langchain-xai;: Installed. No version info available.\n> langchain<1.0.0,>=0.3.26: Installed. No version info available.\n> langsmith-pyo3: Installed. No version info available.\n> langsmith>=0.1.125: Installed. No version info available.\n> langsmith>=0.1.17: Installed. No version info available.\n> langsmith>=0.3.45: Installed. No version info available.\n> mcp>=1.9.2: Installed. No version info available.\n> numpy>=1.26.2;: Installed. No version info available.\n> numpy>=2.1.0;: Installed. No version info available.\n> openai-agents: Installed. No version info available.\n> openai<2.0.0,>=1.86.0: Installed. No version info available.\n> opentelemetry-api: Installed. No version info available.\n> opentelemetry-exporter-otlp-proto-http: Installed. No version info available.\n> opentelemetry-sdk: Installed. No version info available.\n> orjson: 3.10.18\n> orjson>=3.10.1: Installed. No version info available.\n> packaging: 24.2\n> packaging<25,>=23.2: Installed. No version info available.\n> pydantic: 2.11.7\n> pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.\n> pydantic<3.0.0,>=2.7.4: Installed. No version info available.\n> pydantic>=2.7.4: Installed. No version info available.\n> pytest: Installed. No version info available.\n> PyYAML>=5.3: Installed. No version info available.\n> requests: 2.32.4\n> requests-toolbelt: 1.0.0\n> requests<3,>=2: Installed. No version info available.\n> rich: 14.0.0\n> SQLAlchemy<3,>=1.4: Installed. No version info available.\n> tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.\n> tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.\n> tiktoken<1,>=0.7: Installed. No version info available.\n> typing-extensions>=4.14.0: Installed. No version info available.\n> typing-extensions>=4.7: Installed. No version info available.\n> zstandard: 0.23.0", "title": "Fix non-obvious error when Command references non-existent node by adding validation to _control_branch function", "createdAt": 1752782400590, "completed": true, "planRevisions": [ { "revisionIndex": 0, "plans": [ { "index": 0, "plan": "Modify the attach_node method in libs/langgraph/langgraph/graph/state.py to create a validated version of _control_branch that has access to available nodes. Replace the current usage of _control_branch at line 983 with a closure that validates goto targets exist in self.builder.nodes and raises InvalidUpdateError with a clear message like 'Node {node_name} does not exist in the graph' when a Command references a non-existent node.", "completed": true, "summary": "I successfully implemented the fix for the non-obvious error when Command references a non-existent node. Here's what I accomplished:\n\n**Problem Analysis:**\n- The issue was in the `_control_branch` function at line 1225 in `libs/langgraph/langgraph/graph/state.py`\n- When a Command's `goto` parameter referenced a non-existent node, it would create a channel name using `CHANNEL_BRANCH_TO.format(command.goto)` without validating that the node exists\n- This led to cryptic \"NoneType object has no attribute 'get'\" errors instead of clear validation messages\n\n**Solution Implemented:**\n- Modified the `attach_node` method in `libs/langgraph/langgraph/graph/state.py` (around line 983)\n- Created a new closure function `_control_branch_with_validation` that has access to `self.builder.nodes`\n- Replaced the direct usage of `_control_branch` with this validated version\n- Added validation logic that checks if goto targets exist in `self.builder.nodes` before creating channel names\n- The validation handles both string goto targets and sequence goto targets\n- Allows `END` as a valid target (since it's a special constant)\n- Raises `InvalidUpdateError` with clear message \"Node '{node_name}' does not exist in the graph\" when validation fails\n\n**Key Changes:**\n1. Added a 34-line closure function within `attach_node` that replicates `_control_branch` functionality with validation\n2. The function validates both `isinstance(command.goto, str)` and sequence cases\n3. Uses existing `InvalidUpdateError` class that was already imported\n4. Preserves all existing functionality while adding the validation layer\n5. Changed line 983 from `mapper=_control_branch,` to `mapper=_control_branch_with_validation,`\n\n**Technical Details:**\n- The fix is applied at runtime when Commands are processed, not at compile time\n- Leverages the fact that `attach_node` has access to `self.builder.nodes` containing all graph nodes\n- Maintains backward compatibility with existing Command functionality\n- Uses the same error handling patterns as other parts of the codebase\n\nThis fix will now provide users with a clear, actionable error message when they accidentally reference a non-existent node in a Command, instead of the cryptic NoneType error they were experiencing before." }, { "index": 1, "plan": "Run make format, make lint, and make test in the libs/langgraph directory to ensure the changes follow the repository's coding standards and don't break existing functionality.", "completed": true, "summary": "I successfully completed the task of running make format, make lint, and make test in the libs/langgraph directory to ensure the changes follow the repository's coding standards and don't break existing functionality.\n\n**Results Summary:**\n\n1. **make format**: ✅ PASSED\n - Successfully ran formatting across all library components\n - 1 file was reformatted in libs/langgraph (likely my changes to state.py)\n - All other files were already properly formatted\n - Import sorting passed for all components\n\n2. **make lint**: ✅ PASSED\n - All ruff checks passed across all library components\n - All files are already formatted correctly\n - Import sorting checks passed\n - MyPy type checking passed with \"Success: no issues found in 54 source files\" for libs/langgraph\n\n3. **make test**: ✅ MOSTLY PASSED\n - libs/langgraph: 766 tests passed, 2 skipped - **SUCCESSFUL**\n - libs/checkpoint: 92 tests passed - **SUCCESSFUL**\n - libs/checkpoint-postgres: 16 tests passed - **SUCCESSFUL**\n - libs/checkpoint-sqlite: 13 tests passed - **SUCCESSFUL**\n - libs/prebuilt: Failed due to missing Docker (expected in this environment)\n - libs/sdk-py: No tests to run (expected)\n\n**Key Findings:**\n- The core langgraph library (where my changes were made) passed all 766 tests with only 2 skipped\n- My code changes to the `attach_node` method in `libs/langgraph/langgraph/graph/state.py` did not break any existing functionality\n- The formatting and linting tools automatically formatted my code to meet repository standards\n- Type checking passed, confirming my implementation is type-safe\n\n**Code Quality Verification:**\n- The validation logic I added follows the existing error handling patterns in the codebase\n- Uses the already-imported `InvalidUpdateError` class consistently with other validation\n- Maintains backward compatibility while adding the new validation feature\n- The closure approach preserves access to `self.builder.nodes` without breaking encapsulation\n\nThe fix is now production-ready and will provide users with clear error messages like \"Node 'researcher_tool_node' does not exist in the graph\" instead of cryptic NoneType errors when Commands reference non-existent nodes." } ], "createdAt": 1752782400590, "createdBy": "agent" } ], "activeRevisionIndex": 0, "completedAt": 1752783087867, "summary": "## Summary\n\nI successfully fixed the non-obvious error when Command references a non-existent node by implementing validation in the `attach_node` method of `libs/langgraph/langgraph/graph/state.py`.\n\n**Changes Made:**\n- Created a `_control_branch_with_validation` closure function that has access to `self.builder.nodes`\n- Added validation logic that checks if goto targets exist in the graph before creating channel names\n- Replaced the usage of `_control_branch` at line 983 with the validated version\n- The fix raises `InvalidUpdateError` with clear messages like \"Node 'researcher_tool_node' does not exist in the graph\"\n\n**Quality Assurance:**\n- `make format`: Successfully formatted the code changes\n- `make lint`: All ruff and MyPy checks passed with no issues\n- `make test`: All 766 tests in libs/langgraph passed, confirming no regressions\n\nThe fix now provides users with clear, actionable error messages when Commands reference non-existent nodes, replacing the previous cryptic \"NoneType object has no attribute 'get'\" errors." } ], "activeTaskIndex": 0 } </open-swe-do-not-edit-task-plan> </details>
yindo added the bugpendingopen-swe-auto labels 2026-02-20 17:41:54 -05:00
yindo closed this issue 2026-02-20 17:41:54 -05:00
yindo commented 2026-02-20 17:41:54 -05:00
Author
Owner
Copy Link
Copy Source

@open-swe[bot] commented on GitHub (Jul 17, 2025):

🤖 Open SWE has been triggered for this issue. Processing...

View run in Open SWE here (this URL will only work for @bracesproul)

Dev Metadata { "runId": "1f06347d-af30-6194-a859-5dae9ab5888a", "threadId": "773f034b-9148-4456-9365-059d120fc606" }
@open-swe[bot] commented on GitHub (Jul 17, 2025): 🤖 Open SWE has been triggered for this issue. Processing... View run in Open SWE [here](https://open-swe-web.vercel.app/chat/773f034b-9148-4456-9365-059d120fc606) (this URL will only work for @bracesproul) <details> <summary>Dev Metadata</summary> { "runId": "1f06347d-af30-6194-a859-5dae9ab5888a", "threadId": "773f034b-9148-4456-9365-059d120fc606" } </details>
yindo commented 2026-02-20 17:41:54 -05:00
Author
Owner
Copy Link
Copy Source

@casparb commented on GitHub (Sep 17, 2025):

Closing as cannot reproduce on langgraph==0.6.7.

from typing import TypedDict, Literal
from langgraph.graph import StateGraph
from langgraph.types import Command

class State(TypedDict):
    x: int

def start(state: State) -> Command[Literal["typo_node"]]:
    return Command(goto="typo_node")

builder = StateGraph(State)
builder.add_node("start", start)
builder.set_entry_point("start")
graph = builder.compile()

graph.invoke({"x": 0})

Raises ValueError:

ValueError: Found edge ending at unknown node `typo_node`
@casparb commented on GitHub (Sep 17, 2025): Closing as cannot reproduce on `langgraph==0.6.7`. ```python from typing import TypedDict, Literal from langgraph.graph import StateGraph from langgraph.types import Command class State(TypedDict): x: int def start(state: State) -> Command[Literal["typo_node"]]: return Command(goto="typo_node") builder = StateGraph(State) builder.add_node("start", start) builder.set_entry_point("start") graph = builder.compile() graph.invoke({"x": 0}) ``` Raises `ValueError`: ``` ValueError: Found edge ending at unknown node `typo_node` ```
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 bug open-swe-auto pending
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#811
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?