gpt-5.6-sol fails in /v1/chat/completions when function tools are used with reasoning_effort

[ChathurangiShyalika]

Description:

When running opencode-agent with model tokenrouter/openai/gpt-5.6-sol, the request fails with a 400 API error during scenario execution.

Error message:

APIError: Function tools with reasoning_effort are not supported for gpt-5.6-sol in /v1/chat/completions. To use function tools, use /v1/responses or set reasoning_effort to 'none'.
Request that failed:

scenario 1 failed for method opencode_agent
Command: uv run opencode-agent --model-id tokenrouter/openai/gpt-5.6-sol --allow-files --allow-bash --workspace-dir /tmp/assetopsbench-opencode-workspaces/openai/gpt-5.6-sol/opencode_agent/tokenrouter-openai-gpt-5.6-sol/opencode_agent_1 --scenario-id 1 --run-id opencode_agent_1 "question"

[ShuxinLin]

anomalyco/opencode#26219 seems this is an issue of opencode, the fix was merged to dev of opencode. currently create a patch for the fix.