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

Prompts not being accepted #7661

New Issue
Open
opened 2026-02-16 18:07:52 -05:00 by yindo · 4 comments
yindo commented 2026-02-16 18:07:52 -05:00
Owner
Copy Link
Copy Source

Originally created by @jparr721 on GitHub (Jan 26, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

I'm trying to figure out the source of a problem I'm having. I just downloaded fresh OpenCode and hooked it up to my remote server running the latest Ollama instance. When I boot up a fresh session in an existing project, I cannot get my prompts to be recognized by OpenCode, which results in it just asking me over and over for steps. Sending follow-ups does not yield any different results.

I am using the latest ollama 0.15.1.

Plugins

None

OpenCode version

1.1.36

Steps to reproduce

  1. Yolo download opencode
  2. Connect to remote instance of ollama

Screenshot and/or share link

Image Image Image

Operating System

MacOS 26.2, Windows 11

Terminal

Ghostty, WezTerm, Windows Terminal

Originally created by @jparr721 on GitHub (Jan 26, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description I'm trying to figure out the source of a problem I'm having. I just downloaded fresh OpenCode and hooked it up to my remote server running the latest Ollama instance. When I boot up a fresh session in an existing project, I cannot get my prompts to be recognized by OpenCode, which results in it just asking me over and over for steps. Sending follow-ups does not yield any different results. I am using the latest ollama 0.15.1. ### Plugins None ### OpenCode version 1.1.36 ### Steps to reproduce 1. Yolo download opencode 2. Connect to remote instance of ollama ### Screenshot and/or share link <img width="1082" height="174" alt="Image" src="https://github.com/user-attachments/assets/8ba9babf-8c9d-496e-9f00-47110d3508a9" /> <img width="1180" height="832" alt="Image" src="https://github.com/user-attachments/assets/6772a65a-2645-4a7c-9819-6e0949643538" /> <img width="1180" height="798" alt="Image" src="https://github.com/user-attachments/assets/5f7061e4-30a3-4de6-a134-4b74d94958e6" /> ### Operating System MacOS 26.2, Windows 11 ### Terminal Ghostty, WezTerm, Windows Terminal
yindo added the windowsbug labels 2026-02-16 18:07:52 -05:00
yindo commented 2026-02-16 18:07:52 -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:

  • #10630: hang when ask questions to opencode with the newest version and local LLM by vllm(0.11.2) - Similar symptoms where local LLM instances hang and don't respond to prompts
  • #10573: Custom provider with Openai compatible API Straico (successfully connected) showing blank output and keep looping - Similar issue with custom/remote model providers showing no output and looping
  • #10673: ver 1.1.36, what leads to the interruption of tool calls, the conversation stoped quite frequently - Related issue about conversation interruption with remote models
  • #10631: ModelNotFoundError causes UI disruption and stack trace instead of friendly error message - May be related to model recognition issues when using remote Ollama instances

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

@github-actions[bot] commented on GitHub (Jan 26, 2026): This issue might be a duplicate of existing issues. Please check: - #10630: hang when ask questions to opencode with the newest version and local LLM by vllm(0.11.2) - Similar symptoms where local LLM instances hang and don't respond to prompts - #10573: Custom provider with Openai compatible API Straico (successfully connected) showing blank output and keep looping - Similar issue with custom/remote model providers showing no output and looping - #10673: ver 1.1.36, what leads to the interruption of tool calls, the conversation stoped quite frequently - Related issue about conversation interruption with remote models - #10631: ModelNotFoundError causes UI disruption and stack trace instead of friendly error message - May be related to model recognition issues when using remote Ollama instances Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 18:07:52 -05:00
Author
Owner
Copy Link
Copy Source

@rmdrake commented on GitHub (Jan 26, 2026):

Same issue here. User entered prompts do not get sent to the models. This happens in Plan and Build.
Yolo downloaded Opencode v1.1.36 for linux via install bash script.
Connected my local Ollama by editing:
.config/opencode/config.json
{ "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "name": "Ollama Local", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "qwen3-coder:30b": { "name": "qwen3-coder:30b" }, "gpt-oss:20b": { "name": "gpt-oss:20b" } } } } }

Image
@rmdrake commented on GitHub (Jan 26, 2026): Same issue here. User entered prompts do not get sent to the models. This happens in Plan and Build. Yolo downloaded Opencode v1.1.36 for linux via install bash script. Connected my local Ollama by editing: `.config/opencode/config.json` `{ "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "name": "Ollama Local", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "qwen3-coder:30b": { "name": "qwen3-coder:30b" }, "gpt-oss:20b": { "name": "gpt-oss:20b" } } } } } ` <img width="1592" height="1370" alt="Image" src="https://github.com/user-attachments/assets/dbb3b418-0e29-4777-8f97-a3ef99f35174" />
yindo commented 2026-02-16 18:07:52 -05:00
Author
Owner
Copy Link
Copy Source

@jparr721 commented on GitHub (Jan 28, 2026):

Figured out a solution:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai",
      "name": "Ollama (lab)",
      "options": {
        "baseURL": "http://localhost:11434/v1",
        "apiKey": "ollama"
      },
      "models": {
        "gpt-oss:120b": {
          "name": "GPT OSS 120b"
        }
      }
    }
  }
}

The docs appear to be incorrect. This configuration:

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "llama2": {
          "name": "Llama 2"
        }
      }
    }
  }
}

Has a bug in how it processes the user input. My above configuration works when you force it to use openai DIRECTLY. I'm not sure why this is the case, but the docs currently propose a broken setup. I'll leave this open but there is a solution to anyone that sees this.

@jparr721 commented on GitHub (Jan 28, 2026): Figured out a solution: ``` { "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai", "name": "Ollama (lab)", "options": { "baseURL": "http://localhost:11434/v1", "apiKey": "ollama" }, "models": { "gpt-oss:120b": { "name": "GPT OSS 120b" } } } } } ``` The docs appear to be incorrect. This configuration: ``` { "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "name": "Ollama (local)", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "llama2": { "name": "Llama 2" } } } } } ``` Has a bug in how it processes the user input. My above configuration works when you force it to use openai DIRECTLY. I'm not sure why this is the case, but the docs currently propose a broken setup. I'll leave this open but there is a solution to anyone that sees this.
yindo commented 2026-02-16 18:07:52 -05:00
Author
Owner
Copy Link
Copy Source

@rmdrake commented on GitHub (Jan 28, 2026):

Confirmed

The suggested configuration changes by @jparr721 worked for me on Linux as well. I was able to change:
"npm": "@ai-sdk/openai-compatible",
to:
"npm": "@ai-sdk/openai",
and add the line:
"apiKey": ""
to make the config.json work as expected.

I tested one at a time, and both changes were required. This worked for gpt-oss:20b and qwen3-coder:30b from ollama models, as well as Cydonia-24B-v4.3-GGUF:Q4_K_M from hugging face. Switching between them via the opencode interface appropriately changed the local running ollama model.

@jparr721 suggestion for a clear documentation change would be a suitable fix to keep others from seeing this issue.

@rmdrake commented on GitHub (Jan 28, 2026): **Confirmed** The suggested configuration changes by @jparr721 worked for me on Linux as well. I was able to change: `"npm": "@ai-sdk/openai-compatible",` to: `"npm": "@ai-sdk/openai",` and add the line: `"apiKey": ""` to make the config.json work as expected. I tested one at a time, and both changes were required. This worked for gpt-oss:20b and qwen3-coder:30b from ollama models, as well as Cydonia-24B-v4.3-GGUF:Q4_K_M from hugging face. Switching between them via the opencode interface appropriately changed the local running ollama model. @jparr721 suggestion for a clear documentation change would be a suitable fix to keep others from seeing this issue.
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 windows
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#7661
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?