feature: Support custom tool parsers

[shantur]

AI SDK provides a capability to allow custom tool parsers documented - https://ai-sdk.dev/docs/ai-sdk-core/middleware#custom-tool-call-parser

Can this be implemented? Maybe atleast the @ai-sdk-tool/parser package. It offers three middlewares OOB

gemmaToolMiddleware: JSON tool calls inside markdown fences. Best for Gemma-like models.
morphXmlToolMiddleware: Plain XML tool calls. Good fit for GLM/GLM-like models.
hermesToolMiddleware: JSON payload wrapped in <tool_call> XML tags. Hermes/Llama-style prompts.

This will allow Opencode to be compatible with a lot of locally hosted models.

It can be an option to set a middleware as part of custom providers configuration for a model. Initially could be just one of these 3 above, maybe down the line a way of providing our own like plugins / custom tools.

[github-actions]

This issue might be a duplicate of existing issues. Please check:

• When calling to vllm server with hermes tool parser opencode doesn't call the tools #1122: Specifically mentions hermes tool parser with vllm server not working with OpenCode, which is one of the exact middlewares you mentioned
• Tool Calling Issues with Open Source Models in OpenCode #234: Addresses tool calling compatibility issues with open source models, which custom tool parsers would solve
• Local Ollama tool calling either not calling or failing outright #1034: Another local model tool calling issue that custom parsers could help resolve
• Tool Calls Section End Token (<|tool_calls_section_end|>) Parsing Failures #1021: Tool parsing failures with various models that custom tool parsers would address

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

[rekram1-node]

would need to look at it more but it sounds reasonable

[minpeter]

I am the maintainer of the ai-sdk-tool-call-middleware project, and I am very willing to support this work.

Thanks for the suggestion, @shantur

[okuyam2y]

I have a working integration of @ai-sdk-tool/parser with OpenCode. Since upstream integration is still pending, I've published it as an experimental fork:

https://github.com/okuyam2y/opencode-nofc

It adds a toolParser option on provider/model config (hermes | hermes-strict | xml) that gates middleware injection plus the finish-reason/tag cleanup those parsers need. Also includes streaming tag filter, stream deduplication, and document extraction (PDF/DOCX/XLSX).

This is experimental and tracks upstream dev branch. If you're hitting this issue with a gateway or provider that doesn't support native function calling, feel free to try it out.

[okuyam2y]

One additional thing that may be worth documenting: reliability with custom tool parsers seems much more model-dependent than with native function calling.

In our testing, higher-capability models such as GPT-5.4 and Claude Sonnet 4.5 were the first ones that were consistently reliable on multi-step review workflows, while lower-tier models often handled simple cases but degraded on longer runs.

If this support lands, it would be helpful for the docs to note that users should validate parser behavior on a representative multi-step workflow before relying on it in production.