anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

hang when ask questions to opencode with the newest version and local LLM by vllm(0.11.2) #7600

New Issue
Open
opened 2026-02-16 18:07:41 -05:00 by yindo · 1 comment
yindo commented 2026-02-16 18:07:41 -05:00
Owner
Copy Link
Copy Source

Originally created by @inv1s10n on GitHub (Jan 26, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

I tried use opencode with a local LLM server with openai API by vllm(0.11.2), but when I ask questions, opencode has no response.
When i firstly ask "hello", it works. When i ask "hello" the second, it has no response, but the vllm works and gpu has utilization.

Plugins

No response

OpenCode version

v1.1.36. build from source code

Steps to reproduce

follows are vllm startup script and opencode logs

Screenshot and/or share link

Image Image Image Image Image Image Image

Operating System

docker image: oven/bun:1-debian

Terminal

No response

Originally created by @inv1s10n on GitHub (Jan 26, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description I tried use opencode with a local LLM server with openai API by vllm(0.11.2), but when I ask questions, opencode has no response. When i firstly ask "hello", it works. When i ask "hello" the second, it has no response, but the vllm works and gpu has utilization. ### Plugins _No response_ ### OpenCode version v1.1.36. build from source code ### Steps to reproduce follows are vllm startup script and opencode logs ### Screenshot and/or share link <img width="525" height="105" alt="Image" src="https://github.com/user-attachments/assets/31fc1c0a-ac5d-4d34-aa1d-cf69aea3b09b" /> <img width="391" height="567" alt="Image" src="https://github.com/user-attachments/assets/d5c525eb-496f-4f3f-87b3-fe169b37b51f" /> <img width="1194" height="43" alt="Image" src="https://github.com/user-attachments/assets/90757492-e7b5-407b-b177-abb3ea629210" /> <img width="1441" height="698" alt="Image" src="https://github.com/user-attachments/assets/d76195c7-6ef9-4f88-a562-c42be9cf0d28" /> <img width="576" height="290" alt="Image" src="https://github.com/user-attachments/assets/75050994-0803-4059-b8c0-314791ef1252" /> <img width="577" height="290" alt="Image" src="https://github.com/user-attachments/assets/b6ae1ff6-6d34-49a0-958f-f54bcfff0904" /> <img width="862" height="161" alt="Image" src="https://github.com/user-attachments/assets/b19741d8-ec21-42dd-acd8-7018e1bb9933" /> ### Operating System docker image: oven/bun:1-debian ### Terminal _No response_
yindo added the bug label 2026-02-16 18:07:41 -05:00
yindo commented 2026-02-16 18:07:42 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 26, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #4255: OpenCode hangs indefinitely with local LLM models due to improper handling of empty tool_calls arrays - exact same symptoms (first request sometimes works, subsequent requests hang)
  • #7185: gpt-oss-120B by vLLM doesn't call tools - tool calling failures with vLLM
  • #7524: gpt-oss-120b unable to call tools with chat/completions endpoint - vLLM tool calling issues
  • #7486: Local Qwen models only return tool parameters but cannot execute tools - vLLM configuration issue
  • #5187: Ollama models receive empty message arrays preventing tool usage
  • #7083: Ollama models return no results despite correct configuration

The root cause appears to be improper handling of empty tool_calls: [] arrays in responses from local LLM servers. This causes OpenCode to wait indefinitely for tool execution that never occurs.

Feel free to ignore if your specific case differs from these issues.

@github-actions[bot] commented on GitHub (Jan 26, 2026): This issue might be a duplicate of existing issues. Please check: - #4255: OpenCode hangs indefinitely with local LLM models due to improper handling of empty tool_calls arrays - exact same symptoms (first request sometimes works, subsequent requests hang) - #7185: gpt-oss-120B by vLLM doesn't call tools - tool calling failures with vLLM - #7524: gpt-oss-120b unable to call tools with chat/completions endpoint - vLLM tool calling issues - #7486: Local Qwen models only return tool parameters but cannot execute tools - vLLM configuration issue - #5187: Ollama models receive empty message arrays preventing tool usage - #7083: Ollama models return no results despite correct configuration The root cause appears to be improper handling of empty `tool_calls: []` arrays in responses from local LLM servers. This causes OpenCode to wait indefinitely for tool execution that never occurs. Feel free to ignore if your specific case differs from these issues.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label 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: anomalyco/opencode#7600
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?