anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-23 10:45:33 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

qwen3-coder-30B-A3B is not able to call any tool #1229

New Issue
Closed
opened 2026-02-16 17:30:05 -05:00 by yindo · 11 comments
yindo commented 2026-02-16 17:30:05 -05:00
Owner
Copy Link
Copy Source

Originally created by @florath on GitHub (Aug 11, 2025).

Originally assigned to: @thdxr on GitHub.

I'm running a self-hosted "cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ" model using vLLM:

python3 -m vllm.entrypoints.openai.api_server --port 8080 --model cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ --tensor-parallel-size 1 --pipeline_parallel_size 3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --max-model-len 262144"

It looks that the model is not able to call any tool (function) with OpenCode 0.4.12:

  ┃                                                                                                                                                                                ┃
  ┃  Todowrite                                                                                                                                                                     ┃
  ┃                                                                                                                                                                                ┃
  ┃  The arguments provided to the tool are invalid: Invalid input for tool todowrite: Type validation failed: Value: {"todos":"[{\"content\": \"Examine the structure of          ┃
  ┃  model/topology.yaml and model/node-metrics.yaml\", \"status\": \"in_progress\", \"priority\": \"high\", \"id\": \"task-1\"}]"}.                                               ┃
  ┃  Error message: [                                                                                                                                                              ┃
  ┃    {                                                                                                                                                                           ┃
  ┃      "code": "invalid_type",                                                                                                                                                   ┃
  ┃      "expected": "array",                                                                                                                                                      ┃
  ┃      "received": "string",                                                                                                                                                     ┃
  ┃      "path": [                                                                                                                                                                 ┃
  ┃        "todos"                                                                                                                                                                 ┃
  ┃      ],                                                                                                                                                                        ┃
  ┃      "message": "Expected array, received string"  


  ┃  Bash                                                                                                                                                                          ┃
  ┃                                                                                                                                                                                ┃
  ┃  The arguments provided to the tool are invalid: Invalid input for tool bash: Type validation failed: Value: {"command":"ls -la model/"}.                                      ┃
  ┃  Error message: [                                                                                                                                                              ┃
  ┃    {                                                                                                                                                                           ┃
  ┃      "code": "invalid_type",                                                                                                                                                   ┃
  ┃      "expected": "string",                                                                                                                                                     ┃
  ┃      "received": "undefined",                                                                                                                                                  ┃
  ┃      "path": [                                                                                                                                                                 ┃
  ┃        "description"                                                                                                                                                           ┃
  ┃      ],                                                                                                                                                                        ┃
  ┃      "message": "Required" 


  ┃                                                                                                                                                                                ┃
  ┃  Bash                                                                                                                                                                          ┃
  ┃                                                                                                                                                                                ┃
  ┃  The arguments provided to the tool are invalid: Invalid input for tool bash: Type validation failed: Value: {"command":"mkdir -p ./tools"}.                                   ┃
  ┃  Error message: [                                                                                                                                                              ┃
  ┃    {                                                                                                                                                                           ┃
  ┃      "code": "invalid_type",                                                                                                                                                   ┃
  ┃      "expected": "string",                                                                                                                                                     ┃
  ┃      "received": "undefined",                                                                                                                                                  ┃
  ┃      "path": [                                                                                                                                                                 ┃
  ┃        "description"                                                                                                                                                           ┃
  ┃      ],                                                                                                                                                                        ┃
  ┃      "message": "Required"

I have the same experience with #1783: not only with the todo tool - but with all tools

I tested also with hermes but in this case there was no tool call at all.

The tests with OpenCode from end of last week run kind of better. At least the basic tools could be used.

Originally created by @florath on GitHub (Aug 11, 2025). Originally assigned to: @thdxr on GitHub. I'm running a self-hosted "cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ" model using vLLM: `python3 -m vllm.entrypoints.openai.api_server --port 8080 --model cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ --tensor-parallel-size 1 --pipeline_parallel_size 3 --enable-auto-tool-choice --tool-call-parser qwen3_coder --max-model-len 262144" ` It looks that the model is not able to call any tool (function) with OpenCode 0.4.12: ``` ┃ ┃ ┃ Todowrite ┃ ┃ ┃ ┃ The arguments provided to the tool are invalid: Invalid input for tool todowrite: Type validation failed: Value: {"todos":"[{\"content\": \"Examine the structure of ┃ ┃ model/topology.yaml and model/node-metrics.yaml\", \"status\": \"in_progress\", \"priority\": \"high\", \"id\": \"task-1\"}]"}. ┃ ┃ Error message: [ ┃ ┃ { ┃ ┃ "code": "invalid_type", ┃ ┃ "expected": "array", ┃ ┃ "received": "string", ┃ ┃ "path": [ ┃ ┃ "todos" ┃ ┃ ], ┃ ┃ "message": "Expected array, received string" ``` ``` ┃ Bash ┃ ┃ ┃ ┃ The arguments provided to the tool are invalid: Invalid input for tool bash: Type validation failed: Value: {"command":"ls -la model/"}. ┃ ┃ Error message: [ ┃ ┃ { ┃ ┃ "code": "invalid_type", ┃ ┃ "expected": "string", ┃ ┃ "received": "undefined", ┃ ┃ "path": [ ┃ ┃ "description" ┃ ┃ ], ┃ ┃ "message": "Required" ``` ``` ┃ ┃ ┃ Bash ┃ ┃ ┃ ┃ The arguments provided to the tool are invalid: Invalid input for tool bash: Type validation failed: Value: {"command":"mkdir -p ./tools"}. ┃ ┃ Error message: [ ┃ ┃ { ┃ ┃ "code": "invalid_type", ┃ ┃ "expected": "string", ┃ ┃ "received": "undefined", ┃ ┃ "path": [ ┃ ┃ "description" ┃ ┃ ], ┃ ┃ "message": "Required" ``` I have the same experience with #1783: not only with the todo tool - but with all tools I tested also with hermes but in this case there was no tool call at all. The tests with OpenCode from end of last week run kind of better. At least the basic tools could be used.
yindo added the model-problem label 2026-02-16 17:30:05 -05:00
yindo closed this issue 2026-02-16 17:30:05 -05:00
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@thdxr commented on GitHub (Aug 11, 2025):

i don't know if there is anything to do on ou rend - we've had good experiences with lmstudio

@thdxr commented on GitHub (Aug 11, 2025): i don't know if there is anything to do on ou rend - we've had good experiences with lmstudio
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 11, 2025):

It would also help to understand where the problem is.
I assume that an LLM’s responses should not vary significantly depending on the underlying middleware.

Here is a trace of the response form the LLM that resulted in the attached error. (Removed one newline for better readability.)

data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":" properly"},"logprobs":null,"finish_reason":null}]}

101
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":" formatted"},"logprobs":null,"finish_reason":null}]}

fc
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":":\n\n"},"logprobs":null,"finish_reason":null}]}

166
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_5e8b4c3144f24e2a95348342","type":"function","index":0,"function":{"name":"bash","arguments":""}}]},"logprobs":null,"finish_reason":null}]}

122
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"logprobs":null,"finish_reason":null}]}

15b
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"command\": \"cd /home/florath/devel/TEST/ttt && ls -la\""}}]},"logprobs":null,"finish_reason":null}]}

122
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"logprobs":null,"finish_reason":null}]}

112
data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"tool_calls","stop_reason":null}]}

e
data: [DONE]

When re-assembling this on the client side this should be the result:

{
  "tool_calls": [
    {
      "id": "call_5e8b4c3144f24e2a95348342",
      "type": "function",
      "index": 0,
      "function": {
        "name": "bash",
        "arguments": {
          "command": "cd /home/florath/devel/TEST/ttt && ls -la"
        }
      }
    }
  ]
}

I'm not an expert in this field, but this looks kind of valid.

But OpenCode logs:

Image

Maybe this helps?

@florath commented on GitHub (Aug 11, 2025): It would also help to understand where the problem is. I assume that an LLM’s responses should not vary significantly depending on the underlying middleware. Here is a trace of the response form the LLM that resulted in the attached error. (Removed one newline for better readability.) ``` data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":" properly"},"logprobs":null,"finish_reason":null}]} 101 data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":" formatted"},"logprobs":null,"finish_reason":null}]} fc data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":":\n\n"},"logprobs":null,"finish_reason":null}]} 166 data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"id":"call_5e8b4c3144f24e2a95348342","type":"function","index":0,"function":{"name":"bash","arguments":""}}]},"logprobs":null,"finish_reason":null}]} 122 data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{"}}]},"logprobs":null,"finish_reason":null}]} 15b data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"command\": \"cd /home/florath/devel/TEST/ttt && ls -la\""}}]},"logprobs":null,"finish_reason":null}]} 122 data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"logprobs":null,"finish_reason":null}]} 112 data: {"id":"chatcmpl-0647664af2c74d868f3580183b7da97d","object":"chat.completion.chunk","created":1754926598,"model":"cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ","choices":[{"index":0,"delta":{"content":""},"logprobs":null,"finish_reason":"tool_calls","stop_reason":null}]} e data: [DONE] ``` When re-assembling this on the client side this should be the result: ``` { "tool_calls": [ { "id": "call_5e8b4c3144f24e2a95348342", "type": "function", "index": 0, "function": { "name": "bash", "arguments": { "command": "cd /home/florath/devel/TEST/ttt && ls -la" } } } ] } ``` I'm not an expert in this field, but this looks kind of valid. But OpenCode logs: <img width="1529" height="417" alt="Image" src="https://github.com/user-attachments/assets/e4969ac8-5abd-48c4-a654-d60bc3ffcee2" /> Maybe this helps?
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 11, 2025):

It looks that this is a problem with the LLM. The response is correctly formatted, but it is missing the description field, which is mandatory.

  parameters: z.object({
    command: z.string().describe("The command to execute"),
    timeout: z.number().describe("Optional timeout in milliseconds").optional(),
    description: z
      .string()
      .describe(
        "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: 
  Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'",
      ),
  }),

The description field is correctly marked as mandatory in the prompt:

 "required":["command","description"]

and

  "description":{
    "type":"string",
    "description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory..."
  }

But the response from the LLM is missing the response field:

{"command": "cd /home/florath/devel/TEST/ttt && ls -la"}

instead of correctly

  {
    "command": "cd /home/florath/devel/TEST/ttt && ls -la",
    "description": "Lists files in directory with details"
  }

For me this is kind of strange that such a model is not capable of handling this correctly. I will try with different settings like tool-call-parser or context length (I just learned that the prompt is about 60k characters).

@florath commented on GitHub (Aug 11, 2025): It looks that this is a problem with the LLM. The response is correctly formatted, but it is missing the description field, which is mandatory. ``` parameters: z.object({ command: z.string().describe("The command to execute"), timeout: z.number().describe("Optional timeout in milliseconds").optional(), description: z .string() .describe( "Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'", ), }), ``` The description field is correctly marked as mandatory in the prompt: ``` "required":["command","description"] ``` and ``` "description":{ "type":"string", "description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory..." } ``` But the response from the LLM is missing the response field: ``` {"command": "cd /home/florath/devel/TEST/ttt && ls -la"} ``` instead of correctly ``` { "command": "cd /home/florath/devel/TEST/ttt && ls -la", "description": "Lists files in directory with details" } ``` For me this is kind of strange that such a model is not capable of handling this correctly. I will try with different settings like tool-call-parser or context length (I just learned that the prompt is about 60k characters).
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 11, 2025):

A random find. Could be related. Maybe anybody tried another quantization or the original?

Image

Source: https://docs.unsloth.ai/basics/qwen3-coder-how-to-run-locally

@florath commented on GitHub (Aug 11, 2025): A random find. Could be related. Maybe anybody tried another quantization or the original? <img width="790" height="104" alt="Image" src="https://github.com/user-attachments/assets/686adbf6-685e-414a-8a37-791fcb932e6c" /> Source: https://docs.unsloth.ai/basics/qwen3-coder-how-to-run-locally
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 12, 2025):

Using a workaround of the above mentioned problem (see #1856) and moving to a version where the tool calling is fixed (unsloth/Qwen3-Coder-30B-A3B-Instruct), the problem disappeared (for now).

@florath commented on GitHub (Aug 12, 2025): Using a workaround of the above mentioned problem (see #1856) and moving to a version where the tool calling is fixed (unsloth/Qwen3-Coder-30B-A3B-Instruct), the problem disappeared (for now).
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 12, 2025):

When running longer sessions, from time to time qwen3-coder just returns invalid JSON. E.g. stringified arrays, missing the "description" from time to time in the bash tool, and so on.

I created a small proxy which fixes the responses from the LLM. Maybe this is also of help for others?
https://github.com/florath/qwen3-call-patch-proxy

I have now a full working OpenCode with qwen3-coder. From my side this issue can be closed.

@florath commented on GitHub (Aug 12, 2025): When running longer sessions, from time to time qwen3-coder just returns invalid JSON. E.g. stringified arrays, missing the "description" from time to time in the bash tool, and so on. I created a small proxy which fixes the responses from the LLM. Maybe this is also of help for others? https://github.com/florath/qwen3-call-patch-proxy I have now a full working OpenCode with qwen3-coder. From my side this issue can be closed.
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@peaster commented on GitHub (Aug 13, 2025):

@florath how are you configuring opencode with your proxy? I'd really like the AWQ quant to work via vLLM

@peaster commented on GitHub (Aug 13, 2025): @florath how are you configuring opencode with your proxy? I'd really like the AWQ quant to work via vLLM
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@florath commented on GitHub (Aug 14, 2025):

Here my provider config:

"provider": {
	"qwen3-coder-30b-a3b-instruct-vllm": {
	    "name": "Qwen 3 Coder 30B (vLLM)",
	    "npm": "@ai-sdk/openai-compatible",
	    "models": {
		  "cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ": {}
	    },
	    "options": {
	  	  "baseURL": "http://127.0.0.1:7999/v1"
	    }
	}
},

For me the proxy is running on the same server as OpenCode. The proxy is then configured to point to my vLLM running the qwen3-coder model.

@florath commented on GitHub (Aug 14, 2025): Here my provider config: ```JSON "provider": { "qwen3-coder-30b-a3b-instruct-vllm": { "name": "Qwen 3 Coder 30B (vLLM)", "npm": "@ai-sdk/openai-compatible", "models": { "cpatonn/Qwen3-Coder-30B-A3B-Instruct-AWQ": {} }, "options": { "baseURL": "http://127.0.0.1:7999/v1" } } }, ``` For me the proxy is running on the same server as OpenCode. The proxy is then configured to point to my vLLM running the qwen3-coder model.
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

@peaster commented on GitHub (Aug 18, 2025):

this works well! thank you. For me, my root issue was a copypasta from an older qwen model that used a different tool call parser. I did run into the other issues you were seeing too

@peaster commented on GitHub (Aug 18, 2025): this works well! thank you. For me, my root issue was a copypasta from an older qwen model that used a different tool call parser. I did run into the other issues you were seeing too
yindo commented 2026-02-16 17:30:05 -05:00
Author
Owner
Copy Link
Copy Source

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

As of opencode v0.5.29, https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 calls tools flawlessly without any changes. I'm able to run that on dual 3090s with a 105,000 token context

vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 --tool-call-parser qwen3_coder --enable-auto-tool-choice --gpu-memory-utilization 0.9 --tensor-parallel-size 2 --max_model_len 105000
Image
@peaster commented on GitHub (Aug 30, 2025): As of opencode v0.5.29, https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 calls tools flawlessly without any changes. I'm able to run that on dual 3090s with a 105,000 token context ``` vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 --tool-call-parser qwen3_coder --enable-auto-tool-choice --gpu-memory-utilization 0.9 --tensor-parallel-size 2 --max_model_len 105000 ``` <img width="719" height="519" alt="Image" src="https://github.com/user-attachments/assets/33f4b413-f7f7-420a-9e72-056c885cdfbe" />
yindo commented 2026-02-16 17:30:06 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Aug 30, 2025):

@florath is this good to close then?

@rekram1-node commented on GitHub (Aug 30, 2025): @florath is this good to close then?
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 model-problem
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#1229
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?