Local Ollama tool calling either not calling or failing outright

[davidvfx07]

Hi, I'm trying a local Ollama model that supports tool calls (qwen3:32b). When I ask for example "What networks am I connected to?" the model just thinks about which tool to use to fulfill the request, but never does anything. Occasionally it will do something, as I've seen with prompts like "What's in my .config files?", and its seemingly correctly generating the tool-call JSON in the ballpark of {"Bash": "LS", ...} or something, but the command never actually executes anything and is just printed to the chat. I'd assume something isn't configured right or maybe the JSON tool call is not formatted correctly after all. I've confirmed it works with Github Copilot GPT-4o, and all tools were enabled in my settings for both Copilot and Ollama. What is the expected workflow to get opencode to actually run the command after the model suggests it?

(I simplified my config for space here to whats important, but nothing else is different except just some other Ollama models I added.)

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": {
        "baseURL": "http://127.0.0.1:11434/v1"
      },
        "qwen3:32b": {
          "name": "Qwen 3 32B (local)"
      }
    }
  }
}

[alfonsodg]

Same here , but i am using litellm in front of ollama for OpenAI compatibility adding a token

[davidvfx07]

Update with more models below.

TLDR, nothing works except cloud models. With Ollama, some models don't acknowledge having access to tools, some do but only explain what they would do and never actually try to do anything with them, some actually try but get the formatting wrong or are simply unrecognized by opencode, and some try to run tools and appear to be recognized by opencode but still don't do anything.

~~~~~~~~~~ OLLAMA ~~~~~~~~~~

Cogito v1 Preview 32B Q4_K_M (cogito:32b)

# Conversation History

---

User (2025-07-16 02:27:00)

What networks am I connect to?

---

Assistant (2025-07-16 02:27:00)

To determine which network your system is connected to, let me first try running some basic commands:

Devstral 24B Q_4_K_M (devstral:24b)

# Conversation History

---

User (2025-07-16 02:29:44)

What networks am I connected to?

---

Assistant (2025-07-16 02:29:44)

I'm unable to directly determine your network connections. However, you can typically find this information by checking your device's network settings or using command-line tools like ifconfig on Unix-based systems or ipconfig on Windows.

If you're looking for guidance on how to check this for a specific operating system, let me know!

Qwen 3 32B (qwen3:32b)

# Conversation History

---

User (2025-07-16 02:33:13)

What networks am I connected to?

---

Assistant (2025-07-16 02:33:13)

Okay, the user is asking, "What networks am I connected to?" Let me think about how to approach this.

First, I need to figure out which tools are available. The provided tools include functions like Glob, Grep, LS, Read, etc. But the user is asking about network connections, which might not be directly accessible through these tools.

Wait, there's the 'Bash' tool. Maybe I can run a command to check network connections. For example, on a Unix-based system, the 'netstat' command or 'ifconfig' could show network interfaces and connections. Alternatively, 'ip a' or 'nmcli' might be useful.

Since the user is likely working in a Linux environment, using 'bash' to execute a command like 'nmcli dev status' could list the network devices and their status. This command is part of NetworkManager, which is common in many Linux distributions.

But I should check if the Bash tool is available. Looking back at the tools listed, there is a 'task' function that launches an agent with access to Bash. So, maybe using the task function to run a Bash command would be the right approach here.

Alternatively, if the system doesn't have NetworkManager, maybe using 'ip a' or 'ifconfig' would be better. But without knowing the exact environment, 'nmcli' is a good starting point.

So, the plan is to use the 'task' function to execute a Bash command that checks network connections. The prompt for the agent should be to run the appropriate command and return the output.

Therefore, the function call would be to the 'task' function with a description "Check network connections" and a prompt instructing the agent to run the Bash command and return the result.

[Tool: task]

[Tool: task]

Okay, the user wants me to display the current network interfaces and their status. They mentioned examples like 'nmcli dev status' or 'ip a'. I need to decide which command to use.

First, I should check which tool is more appropriate here. The 'ip a' command is part of the iproute2 suite and shows all network interfaces along with their addresses and status. The 'nmcli dev status' command is specific to NetworkManager and shows the status of devices managed by it. Since the user is asking for a general overview, 'ip a' might be more comprehensive as it doesn't rely on NetworkManager being present.

However, I should consider the environment. If the system uses NetworkManager, then 'nmcli' would provide useful info. But without knowing the system's configuration, I should opt for a command that's more universally available. 'ip a' is part of the standard Linux tools, so it's safer to use that.

So the correct function call is to execute 'ip a' using the Bash execute function. That should display all interfaces and their details.

Qwen2.5 Coder 32B Instruct IQ3_M (krith/qwen2.5-coder-32b-instruct:IQ3_M)

# Conversation History

---

User (2025-07-16 02:45:50)

What networks am I connected to?

---

Assistant (2025-07-16 02:45:50)

{"name": "task", "arguments": {"description": "Check network connections", "prompt": "Research and report the current network connections by using system commands like ipconfig (Windows) or ifconfig/ifdata (Linux)."}}

---

User (2025-07-16 02:46:09)

What is Rust?

---

Assistant (2025-07-16 02:46:09)

To provide information about Rust without launching an agent or reading specific files, I can summarize the key points about Rust here:

Rust is a systems programming language created by Mozilla Research. It aims to empower all developers to build reliable and efficient software. Rust does this by providing low-level control over hardware resources while also preventing many of the errors that plague other languages at compile time.

Key features of Rust include:

• Memory Safety: Rust prevents null pointer dereferences, buffer overflows, and data races through its ownership system.
• Concurrency: Rust's ownership model ensures thread safety without heavy runtime overhead, supported by powerful concurrency primitives like threads and async/await.
• Performance: Performance is comparable to C++ while offering memory safety, eliminating the need for a garbage collector or manual memory management in most cases.
• Toolchain: Rust comes with Cargo, its package manager and build system, which streamlines dependency management and project creation.

If you would like more detailed information about Rust, such as specific features, use cases, or comparisons to other languages, please let me know!

---

User (2025-07-16 02:46:27)

Whats my username?

---

Assistant (2025-07-16 02:46:27)

I don't have access to your specific system information or user settings, so I can't provide your username. If you need to find out your username on a particular system, you might consider checking the terminal on Linux or macOS by running whoami, or on Windows by typing echo %username% in Command Prompt.

Is there something else specific you'd like help with?

---

User (2025-07-16 02:46:38)

What networks am I connected to?

---

Assistant (2025-07-16 02:46:38)

task {"description": "check network connections", "prompt": "Identify all active network interfaces and their IP addresses on the local machine. Do not write code; just return a concise summary of the network connections."}

~~~~~~~~~~ CLOUD ~~~~~~~~~~

GPT4o via GitHub Copilot (it doesn't say but it ran nmcli, iwconfig, and ifconfig which is great. Local IPs hidden in paranoia.)

# Conversation History

---

User (2025-07-16 02:39:08)

What networks am I connected to?

---

Assistant (2025-07-16 02:39:08)

[Tool: bash]

[Tool: bash]

[Tool: bash]

[Tool: bash]

You are connected to the following networks:

1. Loopback (lo):

   • IPv4: 127.0.0.1
   • IPv6: ::1

2. Ethernet (enp7s0):

   • IPv4: ###.###.###.###/24 (Dynamic)
   • IPv6: ####:####:####:####:####:####:####:#### (Global, Dynamic)
   • IPv6: ####::####:####:####:#### (Link-local)

3. Wi-Fi (wlp8s0):

   • IPv4: ###.###.###.###/24 (Dynamic)
   • IPv6: ####::####:####:####:#### (Link-local)

Let me know if you need further details or assistance!

Claude Sonnet 3.5 via GitHub Copilot

# Conversation History

---

User (2025-07-16 02:58:27)

What networks am I connected to?

---

Assistant (2025-07-16 02:58:27)

[Tool: bash]

[Tool: bash]

You are connected to:

• Local network (###.###.###.### via ethernet
• Wireless network (###.###.###.###)

[thdxr]

local LLMs are not yet ready for this kind of workload

[alfonsodg]

Please explain... in my startup we use all the big models but also we have a big server with devstral, deepseek and qwen that helps a lot to develop... exactly what problems have local LLMs ?

[davidvfx07]

Interesting. Is this an inherent issue with open models, like limited parameter count or with how open models are fine-tuned at the moment for tool calling? Either way, projects like open-interpreter seem to circumvent this, I think by ditching the standard tool calling protocol or something like that. Could open-interpreter be integrated, available as a provider, or possibly be given an openai compatible API and local endpoint of its own just like Ollama has?

[alfonsodg]

In fact we are using ollama but with litellm for openai compatibility.
And we are coding really well with cline or kilocode however i prefer the cli and right now i haven't tested a good cli coding agent Open source. For that we mainly use géminis code assist and Amazon q developer

[renich]

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:

• 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:

{
    "$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.

[thdxr]

thanks for writing that up!

to clarify what i said earlier - what i meant was the majority of models do not have a great out of the box experience for the type of workload that opencode asks from them

calling tools in a loop, being persistent, working around mistakes/errors

sonnet, gpt4.1, and k2 are good at this workload

other models can be made to work by playing with system prompt / parameters but we likely need research like the above post to figure out how to get them to behave well

[fantomac]

@renich
Thanks a lot, it's working for me with qwen3:14b directly from Ollama (not with docker).
I just /set and /save parameter num_ctx 16384

[pbrass]

When I use mlx-omni-server to serve Qwen3-Coder, I can easily get it to call tools, but opencode doesn't perform the tool calls:
list files in the current directory
pbrass (10:00 PM)

[lists files in the current directory]

<tool_call> <function=list> <parameter=path> /Users/pbrass/ai/test1 </tool_call>
mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit (10:00 PM)

The model sends the <tool_call> request, but for some reason it doesn't get executed. I feel like I"m this close to getting it working. I wonder what part of response parsing isn't working.

[ggaabe]

similar tool call issue for me; it was working a couple weeks ago with devstral, wondering if a new error was introduced