anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-23 02:36:57 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

OpenAI OSS tool calling #1115

New Issue
Closed
opened 2026-02-16 17:29:31 -05:00 by yindo · 6 comments
yindo commented 2026-02-16 17:29:31 -05:00
Owner
Copy Link
Copy Source

Originally created by @Syazvinski on GitHub (Aug 5, 2025).

Originally assigned to: @thdxr on GitHub.

When running through LM Studio, it seems the new template for tools that the OpenAI OSS models use is different and causes premature reasoning to end. Not sure if this is an issue for LM Studio to solve or for Opencode to support.

This is my config

        "npm": "@ai-sdk/openai-compatible",
        "options": {
          "baseURL": "url here"
        },
        "models": {
          "openai/gpt-oss-20b": {
          "name": "Local Model LM Studio",
          "tool_call": true,
          "reasoning": true,
          "limit": {
            "context": 128000,
            "output": 128000
          },
           "options": {
            "tools": true,
            "reasoning": true
          }
          }
        }
    },```
Originally created by @Syazvinski on GitHub (Aug 5, 2025). Originally assigned to: @thdxr on GitHub. When running through LM Studio, it seems the new template for tools that the OpenAI OSS models use is different and causes premature reasoning to end. Not sure if this is an issue for LM Studio to solve or for Opencode to support. This is my config ``` "local": { "npm": "@ai-sdk/openai-compatible", "options": { "baseURL": "url here" }, "models": { "openai/gpt-oss-20b": { "name": "Local Model LM Studio", "tool_call": true, "reasoning": true, "limit": { "context": 128000, "output": 128000 }, "options": { "tools": true, "reasoning": true } } } },```
yindo closed this issue 2026-02-16 17:29:31 -05:00
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@cksac commented on GitHub (Aug 6, 2025):

looks like gpt-oss is trained with https://cookbook.openai.com/articles/openai-harmony#function-calling?
the final prompt should follow openai-harmony format to achieve better result.

@cksac commented on GitHub (Aug 6, 2025): looks like gpt-oss is trained with https://cookbook.openai.com/articles/openai-harmony#function-calling? the final prompt should follow openai-harmony format to achieve better result.
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@jgontrum commented on GitHub (Aug 6, 2025):

AFAIK opencode uses AI SDK which handles the final formatting of the prompts for the used mode/provider. Wouldn’t be surprised if they release an update soon, they seem quite active

@jgontrum commented on GitHub (Aug 6, 2025): AFAIK opencode uses AI SDK which handles the final formatting of the prompts for the used mode/provider. Wouldn’t be surprised if they release an update soon, they seem quite active
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@Ronuhz commented on GitHub (Aug 6, 2025):

Yeah either something goes very wrong with tool calls in OpenCode or the AI SDK, or this model sucks at tool calling.

@Ronuhz commented on GitHub (Aug 6, 2025): Yeah either something goes very wrong with tool calls in OpenCode or the AI SDK, or this model sucks at tool calling.
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@thdxr commented on GitHub (Aug 6, 2025):

it's both - the model sucks at tool calling but parsing these harmony formats is up to the provider - in this case LM Studio

i did think they pushed an update for it though?

@thdxr commented on GitHub (Aug 6, 2025): it's both - the model sucks at tool calling but parsing these harmony formats is up to the provider - in this case LM Studio<br><br>i did think they pushed an update for it though?
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@cksac commented on GitHub (Aug 7, 2025):

harmony formats is not only about model output, which is cater by the provider.
but also the application prompt requirements to achive best result when using gpt-oss.
If application required tool call using XML format, it most will failed at first shot as it mostly add <|constrain|>json before message, causing the model response in json format when tool call.

If application expect xml tool call foramt, add following to the prompt will help

1. USE XML format for all tool calls
2. DON'T add <|constrain|>json for tool calls
@cksac commented on GitHub (Aug 7, 2025): harmony formats is not only about model output, which is cater by the provider. but also the application prompt requirements to achive best result when using gpt-oss. If application required tool call using XML format, it most will failed at first shot as it mostly add `<|constrain|>json` before message, causing the model response in json format when tool call. If application expect xml tool call foramt, add following to the prompt will help ``` 1. USE XML format for all tool calls 2. DON'T add <|constrain|>json for tool calls ```
yindo commented 2026-02-16 17:29:31 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Dec 27, 2025):

[automated] Closing due to 90+ days of inactivity. Feel free to reopen if you still need this!

@rekram1-node commented on GitHub (Dec 27, 2025): [automated] Closing due to 90+ days of inactivity. Feel free to reopen if you still need this!
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#1115
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?