anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 18:25:32 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Nemotron seems to ignore my request when using ollama #3947

New Issue
Open
opened 2026-02-16 17:42:03 -05:00 by yindo · 2 comments
yindo commented 2026-02-16 17:42:03 -05:00
Owner
Copy Link
Copy Source

Originally created by @karthikappy on GitHub (Dec 28, 2025).

Originally assigned to: @rekram1-node on GitHub.

Description

I am trying to use a local LLM (nemotron-3-nano:30b) via ollama to run opencode.
When I send a message in plan mode, I get a response stating that the model is in plan mode but has not received a request.
I get a similar response in build mode (but sometimes i get tool calls that error out in the response.

OpenCode version

1.0.206

Steps to reproduce

  1. Install ollama
  2. Install opencode via npm
  3. Create a new folder and create an opencode.json file
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "http://127.0.0.1:11434/v1",
      },
      "models": {
        "nemotron-3-nano:30b": {}
      }
    }
  }
}
  1. Open a terminal in the current directory and start opencode, select the correct model and try to send a message

Screenshot and/or share link

https://opncd.ai/share/b5WLRobS

Operating System

Windows 11

Terminal

Windows Terminal

Originally created by @karthikappy on GitHub (Dec 28, 2025). Originally assigned to: @rekram1-node on GitHub. ### Description I am trying to use a local LLM (nemotron-3-nano:30b) via ollama to run opencode. When I send a message in plan mode, I get a response stating that the model is in plan mode but has not received a request. I get a similar response in build mode (but sometimes i get tool calls that error out in the response. ### OpenCode version 1.0.206 ### Steps to reproduce 1. Install ollama 2. Install opencode via npm 3. Create a new folder and create an opencode.json file ```json { "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "http://127.0.0.1:11434/v1", }, "models": { "nemotron-3-nano:30b": {} } } } } ``` 4. Open a terminal in the current directory and start opencode, select the correct model and try to send a message ### Screenshot and/or share link https://opncd.ai/share/b5WLRobS ### Operating System Windows 11 ### Terminal Windows Terminal
yindo added the bug label 2026-02-16 17:42:03 -05:00
yindo commented 2026-02-16 17:42:03 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Dec 28, 2025):

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

  • #5694: Local Ollama models are not agentic
  • #5187: Ollama: User message content arrives as empty array - model cannot see user input
  • #6223: Model not returning the answers (Qwen 2.5 Coder with Ollama)

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Dec 28, 2025): This issue might be a duplicate of existing issues. Please check: - #5694: Local Ollama models are not agentic - #5187: Ollama: User message content arrives as empty array - model cannot see user input - #6223: Model not returning the answers (Qwen 2.5 Coder with Ollama) Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:42:03 -05:00
Author
Owner
Copy Link
Copy Source

@karthikappy commented on GitHub (Dec 29, 2025):

After looking through the existing issues and doing some more searching I came across a solutionthat seems to have worked for me.
The default context length in Ollama is 4096 tokens.
The easiest way to change this is actually from the ollama desktop application, Simply go into settings and move the slider to change the default context length. I changed mine to 32768
See: https://docs.ollama.com/context-length

@karthikappy commented on GitHub (Dec 29, 2025): After looking through the existing issues and doing some more searching I came across a solutionthat seems to have worked for me. The default context length in Ollama is 4096 tokens. The easiest way to change this is actually from the ollama desktop application, Simply go into settings and move the slider to change the default context length. I changed mine to 32768 See: https://docs.ollama.com/context-length
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#3947
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?