Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3248] [BUG]: Agent flow model problem #2089

New Issue
Closed
opened 2026-02-22 18:28:06 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:28:06 -05:00
Owner
Copy Link
Copy Source

Originally created by @ctcanbol on GitHub (Feb 17, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3248

Originally assigned to: @shatfield4, @timothycarambat on GitHub.

How are you running AnythingLLM?

Docker (remote machine)

What happened?

I am using the latest version of AnythingLLM on Ubuntu 22.04 with Docker. The LLM for my workspace is llama3.1:8b, system LLM is Deepseek-r1:8b. I created an agent flow to call an API. At first i did not specify any custom LLM for agent calling inside the workspace. And got below error. Then tried setting workspace agent's model manually to llama3.1:8b as same as the workspace model, get the same error. Agent runs and founds the right flow, runs the API but somehow triggers OpenAI LLM, which set nowhere.

[backend] info: [AgentHandler] Attached flow flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865 (json-engine-api api call) plugin to Agent cluster
[backend] info: [AgentLLM - llama3.1:8b] Valid tool call found - running flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865.
[backend] info: [AgentHandler] [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool
[backend] info: [AgentHandler] LLM processing failed: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }). Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }).
     at new OpenAI (/app/server/node_modules/openai/index.js:53:19)
     at new OpenAIProvider (/app/server/utils/agents/aibitat/providers/openai.js:51:20)
     at AIbitat.getProviderForConfig (/app/server/utils/agents/aibitat/index.js:755:16)
     at executeLLMInstruction (/app/server/utils/agentFlows/executors/llm-instruction.js:28:30)
     at FlowExecutor.executeStep (/app/server/utils/agentFlows/executor.js:86:24)
     at FlowExecutor.executeFlow (/app/server/utils/agentFlows/executor.js:127:35)
     at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
     at async AgentFlows.executeFlow (/app/server/utils/agentFlows/index.js:157:12)
     at async Object.handler (/app/server/utils/agentFlows/index.js:213:30)
     at async AIbitat.handleExecution (/app/server/utils/agents/aibitat/index.js:634:22)

1/8 Agent @agent invoked. Swapping over to agent chat. Type /exit to exit agent execution loop early.
2/8 [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool
3/8 Executing flow: json-engine-api api call
4/8 Making POST request to external API...
5/8 Sending body to http://172.16.5.63:31292/json-engine-api/v1/retrieve-json-data-editor: {"screenCode":"gdpr"}
6/8 API call completed
7/8 Processing data with LLM instruction...
8/8 Sending request to LLM...
9/9 Flow failed: Unknown error

Are there known steps to reproduce?

I can reproduce the issue on my environment.

Originally created by @ctcanbol on GitHub (Feb 17, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3248 Originally assigned to: @shatfield4, @timothycarambat on GitHub. ### How are you running AnythingLLM? Docker (remote machine) ### What happened? I am using the latest version of AnythingLLM on Ubuntu 22.04 with Docker. The LLM for my workspace is llama3.1:8b, system LLM is Deepseek-r1:8b. I created an agent flow to call an API. At first i did not specify any custom LLM for agent calling inside the workspace. And got below error. Then tried setting workspace agent's model manually to llama3.1:8b as same as the workspace model, get the same error. Agent runs and founds the right flow, runs the API but somehow triggers OpenAI LLM, which set nowhere. ``` [backend] info: [AgentHandler] Attached flow flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865 (json-engine-api api call) plugin to Agent cluster [backend] info: [AgentLLM - llama3.1:8b] Valid tool call found - running flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865. [backend] info: [AgentHandler] [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool [backend] info: [AgentHandler] LLM processing failed: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }). Error: The OPENAI_API_KEY environment variable is missing or empty; either provide it, or instantiate the OpenAI client with an apiKey option, like new OpenAI({ apiKey: 'My API Key' }). at new OpenAI (/app/server/node_modules/openai/index.js:53:19) at new OpenAIProvider (/app/server/utils/agents/aibitat/providers/openai.js:51:20) at AIbitat.getProviderForConfig (/app/server/utils/agents/aibitat/index.js:755:16) at executeLLMInstruction (/app/server/utils/agentFlows/executors/llm-instruction.js:28:30) at FlowExecutor.executeStep (/app/server/utils/agentFlows/executor.js:86:24) at FlowExecutor.executeFlow (/app/server/utils/agentFlows/executor.js:127:35) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async AgentFlows.executeFlow (/app/server/utils/agentFlows/index.js:157:12) at async Object.handler (/app/server/utils/agentFlows/index.js:213:30) at async AIbitat.handleExecution (/app/server/utils/agents/aibitat/index.js:634:22) ``` ``` 1/8 Agent @agent invoked. Swapping over to agent chat. Type /exit to exit agent execution loop early. 2/8 [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool 3/8 Executing flow: json-engine-api api call 4/8 Making POST request to external API... 5/8 Sending body to http://172.16.5.63:31292/json-engine-api/v1/retrieve-json-data-editor: {"screenCode":"gdpr"} 6/8 API call completed 7/8 Processing data with LLM instruction... 8/8 Sending request to LLM... 9/9 Flow failed: Unknown error ``` ### Are there known steps to reproduce? I can reproduce the issue on my environment.
yindo added the possible buginvestigating labels 2026-02-22 18:28:06 -05:00
yindo closed this issue 2026-02-22 18:28:06 -05:00
yindo commented 2026-02-22 18:28:07 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Feb 17, 2025):

What is your System LLM preference and what is your Workspace agent model (if set at all)
cc: @shatfield4

@timothycarambat commented on GitHub (Feb 17, 2025): What is your System LLM preference and what is your Workspace agent model (if set at all) cc: @shatfield4
yindo commented 2026-02-22 18:28:07 -05:00
Author
Owner
Copy Link
Copy Source

@ctcanbol commented on GitHub (Feb 17, 2025):

System:

Image

Workspace:

Image

Workspace Agent:

Image

P.S: with this configuration and setting workspace agent to default system does not matter; both returns same error.

@ctcanbol commented on GitHub (Feb 17, 2025): System: ![Image](https://github.com/user-attachments/assets/18cae9d4-a024-4a82-a951-db4149b297cc) Workspace: ![Image](https://github.com/user-attachments/assets/30699adc-89f0-4e91-86b5-9df060bf61ad) Workspace Agent: ![Image](https://github.com/user-attachments/assets/b9a48b1a-d3af-41dd-a9be-f759eda19b0b) P.S: with this configuration and setting workspace agent to default system does not matter; both returns same error.
yindo commented 2026-02-22 18:28:07 -05:00
Author
Owner
Copy Link
Copy Source

@ctcanbol commented on GitHub (Feb 19, 2025):

Thanks for the quick fix!

Now after using latest version, the error message changed:

 [backend] info: [AgentLLM - llama3.1:8b] Valid tool call found - running flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865.
 [backend] info: [AgentHandler] [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool
 [backend] info: [AgentHandler] [AgentFlowToolExecutor] - executing API Call block
 [backend] info: [AgentHandler] [AgentFlowToolExecutor] - executing LLM Instruction block
 [backend] info: [AgentHandler] Sending request to LLM (ollama::llama3.1:8b)
 [backend] info: [AgentHandler] LLM processing failed: Cannot read properties of null (reading 'length') TypeError: Cannot read properties of null (reading 'length')
     at OllamaProvider.complete (/app/server/utils/agents/aibitat/providers/ollama.js:49:21)
     at executeLLMInstruction (/app/server/utils/agentFlows/executors/llm-instruction.js:34:39)
     at FlowExecutor.executeStep (/app/server/utils/agentFlows/executor.js:87:24)
     at FlowExecutor.executeFlow (/app/server/utils/agentFlows/executor.js:129:35)
     at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
     at async AgentFlows.executeFlow (/app/server/utils/agentFlows/index.js:151:12)
     at async Object.handler (/app/server/utils/agentFlows/index.js:202:30)
     at async AIbitat.handleExecution (/app/server/utils/agents/aibitat/index.js:634:22)
     at async AIbitat.reply (/app/server/utils/agents/aibitat/index.js:578:21)
     at async AIbitat.chat (/app/server/utils/agents/aibitat/index.js:374:15)
@ctcanbol commented on GitHub (Feb 19, 2025): Thanks for the quick fix! Now after using latest version, the error message changed: ``` [backend] info: [AgentLLM - llama3.1:8b] Valid tool call found - running flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865. [backend] info: [AgentHandler] [debug]: @agent is attempting to call `flow_78fcd5ca-aab0-49e4-8fed-e7a79f473865` tool [backend] info: [AgentHandler] [AgentFlowToolExecutor] - executing API Call block [backend] info: [AgentHandler] [AgentFlowToolExecutor] - executing LLM Instruction block [backend] info: [AgentHandler] Sending request to LLM (ollama::llama3.1:8b) [backend] info: [AgentHandler] LLM processing failed: Cannot read properties of null (reading 'length') TypeError: Cannot read properties of null (reading 'length') at OllamaProvider.complete (/app/server/utils/agents/aibitat/providers/ollama.js:49:21) at executeLLMInstruction (/app/server/utils/agentFlows/executors/llm-instruction.js:34:39) at FlowExecutor.executeStep (/app/server/utils/agentFlows/executor.js:87:24) at FlowExecutor.executeFlow (/app/server/utils/agentFlows/executor.js:129:35) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async AgentFlows.executeFlow (/app/server/utils/agentFlows/index.js:151:12) at async Object.handler (/app/server/utils/agentFlows/index.js:202:30) at async AIbitat.handleExecution (/app/server/utils/agents/aibitat/index.js:634:22) at async AIbitat.reply (/app/server/utils/agents/aibitat/index.js:578:21) at async AIbitat.chat (/app/server/utils/agents/aibitat/index.js:374:15) ```
yindo changed title from [BUG]: Agent flow model problem to [GH-ISSUE #3248] [BUG]: Agent flow model problem 2026-06-05 14:44:29 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label investigating possible bug
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: Mintplex-Labs/anything-llm#2089
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?