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

Tool use with Ollama models. #764

New Issue
Open
opened 2026-02-16 17:28:12 -05:00 by yindo · 12 comments
yindo commented 2026-02-16 17:28:12 -05:00
Owner
Copy Link
Copy Source

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

Originally assigned to: @thdxr on GitHub.

using latest ollama version and tool capable models, executions of tool calls seems to be aborted.

Models are not keen to use tool calls, but could be encourage to at least attempt for one but result fails.

Image

opencode.json file;

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "qwen3:30b": {
            "name": "Qwen3:30b 65k MoE - local",
            "tools": true,
            "reasoning": true,
            "options": { "num_ctx": 65536 }
        },
        "devstral": {
            "name": "Devstral 14b Dense - local",
            "tools": true,
            "reasoning": false,
            "options": { "num_ctx": 131072 }
        }
      }
    },
    "moonshot": {
      "id": "moonshot",
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.moonshot.cn/v1"
       },
      "models": {
        "kimi-k2-0711-preview": {
          "name": "kimi-k2-0711-preview",
          "cost": {
            "input": 0.001953125,
            "output": 0.009765625
          }
        }
      }
    }
  }
}

My hack to have this work on NixOS.

{ pkgs, ... }:

let
  opencodeBin = "/home/berkay/.opencode/bin/opencode";
  configSource = "/home/berkay/.config/opencode/providers/opencode.json";
  authSource = "/home/berkay/.local/share/opencode/auth.json";
  wrapper = pkgs.writeShellScriptBin "opencode" ''
    #!${pkgs.bash}/bin/bash

    CONFIG_SOURCE="${configSource}"
    CONFIG_LINK="./opencode.json"
    AUTH_SOURCE="${authSource}"
    AUTH_LINK="./auth.json"
    
    # Symlink config if not present
    CLEANUP_CONFIG_SYMLINK=0
    if [ ! -f "$CONFIG_LINK" ]; then
      ln -s "$CONFIG_SOURCE" "$CONFIG_LINK"
      CLEANUP_CONFIG_SYMLINK=1
    fi
    # Symlink auth if not present
    CLEANUP_AUTH_SYMLINK=0
    if [ ! -f "$AUTH_LINK" ]; then
      ln -s "$AUTH_SOURCE" "$AUTH_LINK"
      CLEANUP_AUTH_SYMLINK=1
    fi
    # Run opencode
    if [ -x "${opencodeBin}" ]; then
      ${pkgs.steam-run}/bin/steam-run "${opencodeBin}" "$@"
      STATUS=$?
    else
      echo "Error: opencode binary not found at ${opencodeBin}"
      exit 1
    fi
    # Remove symlinks if we created them
    if [ "$CLEANUP_CONFIG_SYMLINK" = "1" ]; then
      rm -f "$CONFIG_LINK"
    fi
    if [ "$CLEANUP_AUTH_SYMLINK" = "1" ]; then
      rm -f "$AUTH_LINK"
    fi
    exit $STATUS
  '';
in
{
  home.packages = [
    pkgs.steam-run
    wrapper
  ];

  xdg.desktopEntries.opencode = {
    name = "OpenCode";
    comment = "AI Coding Agent TUI";
    exec = "opencode";
    icon = "utilities-terminal";
    categories = [ "Development" ];
    terminal = true;
    startupNotify = false;
  };

  xdg.enable = true;
}
Originally created by @Berkyx on GitHub (Jul 16, 2025). Originally assigned to: @thdxr on GitHub. using latest ollama version and tool capable models, executions of tool calls seems to be aborted. Models are not keen to use tool calls, but could be encourage to at least attempt for one but result fails. <img width="2560" height="1440" alt="Image" src="https://github.com/user-attachments/assets/71aa7bd3-5109-4ad8-aa32-f872da2e2faf" /> opencode.json file; ``` { "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "qwen3:30b": { "name": "Qwen3:30b 65k MoE - local", "tools": true, "reasoning": true, "options": { "num_ctx": 65536 } }, "devstral": { "name": "Devstral 14b Dense - local", "tools": true, "reasoning": false, "options": { "num_ctx": 131072 } } } }, "moonshot": { "id": "moonshot", "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "https://api.moonshot.cn/v1" }, "models": { "kimi-k2-0711-preview": { "name": "kimi-k2-0711-preview", "cost": { "input": 0.001953125, "output": 0.009765625 } } } } } } ``` My hack to have this work on NixOS. ``` { pkgs, ... }: let opencodeBin = "/home/berkay/.opencode/bin/opencode"; configSource = "/home/berkay/.config/opencode/providers/opencode.json"; authSource = "/home/berkay/.local/share/opencode/auth.json"; wrapper = pkgs.writeShellScriptBin "opencode" '' #!${pkgs.bash}/bin/bash CONFIG_SOURCE="${configSource}" CONFIG_LINK="./opencode.json" AUTH_SOURCE="${authSource}" AUTH_LINK="./auth.json" # Symlink config if not present CLEANUP_CONFIG_SYMLINK=0 if [ ! -f "$CONFIG_LINK" ]; then ln -s "$CONFIG_SOURCE" "$CONFIG_LINK" CLEANUP_CONFIG_SYMLINK=1 fi # Symlink auth if not present CLEANUP_AUTH_SYMLINK=0 if [ ! -f "$AUTH_LINK" ]; then ln -s "$AUTH_SOURCE" "$AUTH_LINK" CLEANUP_AUTH_SYMLINK=1 fi # Run opencode if [ -x "${opencodeBin}" ]; then ${pkgs.steam-run}/bin/steam-run "${opencodeBin}" "$@" STATUS=$? else echo "Error: opencode binary not found at ${opencodeBin}" exit 1 fi # Remove symlinks if we created them if [ "$CLEANUP_CONFIG_SYMLINK" = "1" ]; then rm -f "$CONFIG_LINK" fi if [ "$CLEANUP_AUTH_SYMLINK" = "1" ]; then rm -f "$AUTH_LINK" fi exit $STATUS ''; in { home.packages = [ pkgs.steam-run wrapper ]; xdg.desktopEntries.opencode = { name = "OpenCode"; comment = "AI Coding Agent TUI"; exec = "opencode"; icon = "utilities-terminal"; categories = [ "Development" ]; terminal = true; startupNotify = false; }; xdg.enable = true; } ```
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@davidvfx07 commented on GitHub (Jul 16, 2025):

#1034 - same issue, frustrating.

@davidvfx07 commented on GitHub (Jul 16, 2025): #1034 - same issue, frustrating.
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@DiedeClaessens commented on GitHub (Jul 17, 2025):

Not a solution, but I have had better success using LMStudio. Important with that one is that you increase context scope of the model

@DiedeClaessens commented on GitHub (Jul 17, 2025): Not a solution, but I have had better success using LMStudio. Important with that one is that you increase context scope of the model
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@leporel commented on GitHub (Jul 17, 2025):

"options": { "num_ctx": 131072 }
Does this work with ollama ? I think this is not supported with openai-compatible https://github.com/ollama/ollama/pull/8938

@leporel commented on GitHub (Jul 17, 2025): `"options": { "num_ctx": 131072 }` Does this work with ollama ? I think this is not supported with openai-compatible https://github.com/ollama/ollama/pull/8938
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@LinkUpGames commented on GitHub (Jul 17, 2025):

"options": { "num_ctx": 131072 } Does this work with ollama ? I think this is not supported with openai-compatible ollama/ollama#8938

Where exactly does the num_ctx field go? I am not really sure where that should go.

@LinkUpGames commented on GitHub (Jul 17, 2025): > `"options": { "num_ctx": 131072 }` Does this work with ollama ? I think this is not supported with openai-compatible [ollama/ollama#8938](https://github.com/ollama/ollama/pull/8938) Where exactly does the `num_ctx` field go? I am not really sure where that should go.
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@renich commented on GitHub (Jul 18, 2025):

OK. ollama user here in Fedora 42.

I was looking for this solution for a while. This is why I'm posting it here (and all issues) for all to know:

@p-lemonish discovered why and the fix is easy: https://github.com/p-lemonish/ollama-x-opencode

In short, download a model that has tool capabilities:

$ ollama show granite3.3:8b
  Model
    architecture        granite    
    parameters          8.2B       
    context length      131072     
    embedding length    4096       
    quantization        Q4_K_M     

  Capabilities
    completion    
    tools         

  License
    Apache License               
    Version 2.0, January 2004    
    ...                          

And edit it so that it has a fixed num_ctx:

```terminal
$ ollama run qwen3:latest
>>> /set parameter num_ctx 16384
Set parameter 'num_ctx' to '16384'
>>> /save qwen3:latest
Created new model 'qwen3:latest'
>>> /bye

After that, you're good to go. Just try it out:

opencode run "generate a todo.md file with the contents 'hello world, from me' in it" --model ollama/qwen3:latest

With a bit of luck, your file will be there.

Credits:

Pre-requisites

  • Your model must be downloaded and functional in ollama.
  • You need to configure your model in opencode.json

My configuration looks like this:

{
    "$schema": "https://opencode.ai/config.json",
    "provider": {
        "ollama": {
            "npm": "@ai-sdk/openai-compatible",
            "options": {
                "baseURL": "http://localhost:11434/v1"
            },
            "models": {
                "granite3.3:8b": {
                    "tools": true
                },
                "mistral-small3.2:24b": {
                    "tools": true
                },
                "qwen3:latest": {
                    "tools": true,
                    "reasoning": true
                }
            }
        }
    }
}

Notes

  • granite3.3 still doesn't work.
@renich commented on GitHub (Jul 18, 2025): OK. ollama user here in Fedora 42. I was looking for this solution for a while. This is why I'm posting it here (and all issues) for all to know: @p-lemonish discovered why and the fix is easy: https://github.com/p-lemonish/ollama-x-opencode In short, download a model that has tool capabilities: ```terminal $ ollama show granite3.3:8b Model architecture granite parameters 8.2B context length 131072 embedding length 4096 quantization Q4_K_M Capabilities completion tools License Apache License Version 2.0, January 2004 ... And edit it so that it has a fixed num_ctx: ```terminal $ ollama run qwen3:latest >>> /set parameter num_ctx 16384 Set parameter 'num_ctx' to '16384' >>> /save qwen3:latest Created new model 'qwen3:latest' >>> /bye ``` After that, you're good to go. Just try it out: ``` opencode run "generate a todo.md file with the contents 'hello world, from me' in it" --model ollama/qwen3:latest ``` With a bit of luck, your file will be there. ## Credits: * https://github.com/p-lemonish/ollama-x-opencode ## Pre-requisites * Your model must be downloaded and functional in ollama. * You need to configure your model in opencode.json My configuration looks like this: ```json { "$schema": "https://opencode.ai/config.json", "provider": { "ollama": { "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "http://localhost:11434/v1" }, "models": { "granite3.3:8b": { "tools": true }, "mistral-small3.2:24b": { "tools": true }, "qwen3:latest": { "tools": true, "reasoning": true } } } } } ``` ## Notes * granite3.3 still doesn't work.
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@azaeldrm commented on GitHub (Aug 30, 2025):

It seems they added OLLAMA_CONTEXT_LENGTH as an env var for Ollama. I'm testing it as we speak, but it seems like it works!

@azaeldrm commented on GitHub (Aug 30, 2025): It seems they added OLLAMA_CONTEXT_LENGTH as an env var for Ollama. I'm testing it as we speak, but it seems like it works!
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@maxolasersquad commented on GitHub (Sep 11, 2025):

The >>> /set parameter num_ctx 16384 from @renich was the key for me. Once I set that on qwen3 the tool usage started working.

@maxolasersquad commented on GitHub (Sep 11, 2025): The `>>> /set parameter num_ctx 16384` from @renich was the key for me. Once I set that on qwen3 the tool usage started working.
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@vdmitriyev commented on GitHub (Sep 26, 2025):

I have a sort of workaround that semi-works for now. The issue is not only the context of ollama, but also a model template. Here how this could be addressed

Pull models

ollama pull qwen3:30b
ollama pull qwen3-coder:30b

View template of existing model:

ollama show qwen3:30b --template

Create initial version of Modelfile-qwen3-coder.dat file (must be manually modified later):

ollama show qwen3:30b --template > Modelfile-qwen3-coder.dat

Edit file with content of the file Modelfile-qwen3-coder.dat manually.
Modelfile-qwen3-coder.dat must start with:

FROM qwen3-coder:30b
PARAMETER num_ctx 32768
TEMPLATE """

Modelfile-qwen3-coder.dat must end it:

"""

Create a new ollama model

ollama create qwen3-coder-32k -f Modelfile-qwen3-coder.dat

Then use qwen3-coder-32k in opencode

P.S. It is not a final solution. But maybe it will save some people a bit of time in searching and trying out different ways of making opencode work with ollama models

@vdmitriyev commented on GitHub (Sep 26, 2025): I have a sort of workaround that semi-works for now. The issue is not only the context of `ollama`, but also a model template. Here how this could be addressed Pull models ```bash ollama pull qwen3:30b ollama pull qwen3-coder:30b ``` View `template` of existing model: ``` ollama show qwen3:30b --template ``` Create initial version of `Modelfile-qwen3-coder.dat` file (must be manually modified later): ``` ollama show qwen3:30b --template > Modelfile-qwen3-coder.dat ``` Edit file with content of the file `Modelfile-qwen3-coder.dat` manually. `Modelfile-qwen3-coder.dat` must start with: ```text FROM qwen3-coder:30b PARAMETER num_ctx 32768 TEMPLATE """ ``` `Modelfile-qwen3-coder.dat` must end it: ```text """ ``` Create a new ollama model ``` ollama create qwen3-coder-32k -f Modelfile-qwen3-coder.dat ``` Then use `qwen3-coder-32k` in opencode P.S. It is not a final solution. But maybe it will save some people a bit of time in searching and trying out different ways of making `opencode` work with `ollama` models
yindo commented 2026-02-16 17:28:12 -05:00
Author
Owner
Copy Link
Copy Source

@BhautikChudasama commented on GitHub (Oct 5, 2025):

How does websearch tool work in ollama?

@BhautikChudasama commented on GitHub (Oct 5, 2025): How does websearch tool work in ollama?
yindo commented 2026-02-16 17:28:13 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 5, 2025):

@BhautikChudasama the tool should just work assuming ollama has enough context set and is presenting it as an option to the llm

@rekram1-node commented on GitHub (Oct 5, 2025): @BhautikChudasama the tool should just work assuming ollama has enough context set and is presenting it as an option to the llm
yindo commented 2026-02-16 17:28:13 -05:00
Author
Owner
Copy Link
Copy Source

@BhautikChudasama commented on GitHub (Oct 5, 2025):

Consider I am running model using llama-cpp? Does websearch or other tool will work? BTW thanks for your reply.

@BhautikChudasama commented on GitHub (Oct 5, 2025): Consider I am running model using llama-cpp? Does websearch or other tool will work? BTW thanks for your reply.
yindo commented 2026-02-16 17:28:13 -05:00
Author
Owner
Copy Link
Copy Source

@maxolasersquad commented on GitHub (Oct 5, 2025):

How does websearch tool work in ollama?

Please do not hijack an issue about one subject to ask a question about another subject.

@maxolasersquad commented on GitHub (Oct 5, 2025): > How does websearch tool work in ollama? Please do not hijack an issue about one subject to ask a question about another subject.
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
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#764
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?