You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
GPT-5.6 (Sol/Terra/Luna) supports reasoning.mode: "pro" on the Responses API: the model performs more work to improve reliability on difficult tasks and returns a single final answer. OpenAI recommends it when quality matters more than latency and token usage. Mux does not expose it yet — this is a known gap from #3702, which shipped GPT-5.6 support with the native max reasoning effort only.
Proposed UX
A toggle inside the thinking slider, shown only when the selected model supports pro mode (GPT-5.6 family). Pro mode is orthogonal to effort (effort: high, mode: pro is valid), so it must not be modeled as a new ThinkingLevel — it composes with whatever level is selected.
Implementation notes (from the reverted spike in #3702)
The @ai-sdk/openai Responses schema only builds reasoning.effort/reasoning.summary; it cannot send reasoning.mode. A working approach mirrored the Anthropic xhigh effort rewrite: emit a Mux-internal header in buildRequestHeaders and have the OpenAI fetch wrapper strip it + inject reasoning.mode into the body on the wire (see 🤖 feat: add GPT-5.6 Sol/Terra/Luna models and move gpt alias to Sol #3702 history, commit 991009e, later reverted).
Gates needed: GPT-5.6 family only (openaiSupportsNativeMaxEffort covers the same family), direct OpenAI routes only (the OpenAI fetch wrapper is not applied on passthrough gateways), Responses wire format only.
Codex review caveat: headless createModel() callers (title generation, advisor streams) never call buildRequestHeaders, so a provider-level config knob needs a fallback path in the wrapper (or explicit plumbing) to apply there.
Live-verified July 9, 2026: reasoning: {"effort": "high", "mode": "pro"} completes on gpt-5.6-sol with a plain API key.
Worth checking whether the AI SDK adds native reasoning.mode support before building the wire-level workaround.
Generated with mux • Model: anthropic:claude-fable-5 • Thinking: high • Cost: $18.71
Summary
GPT-5.6 (Sol/Terra/Luna) supports
reasoning.mode: "pro"on the Responses API: the model performs more work to improve reliability on difficult tasks and returns a single final answer. OpenAI recommends it when quality matters more than latency and token usage. Mux does not expose it yet — this is a known gap from #3702, which shipped GPT-5.6 support with the nativemaxreasoning effort only.Proposed UX
A toggle inside the thinking slider, shown only when the selected model supports pro mode (GPT-5.6 family). Pro mode is orthogonal to effort (
effort: high, mode: prois valid), so it must not be modeled as a newThinkingLevel— it composes with whatever level is selected.Implementation notes (from the reverted spike in #3702)
@ai-sdk/openaiResponses schema only buildsreasoning.effort/reasoning.summary; it cannot sendreasoning.mode. A working approach mirrored the Anthropic xhigh effort rewrite: emit a Mux-internal header inbuildRequestHeadersand have the OpenAI fetch wrapper strip it + injectreasoning.modeinto the body on the wire (see 🤖 feat: add GPT-5.6 Sol/Terra/Luna models and move gpt alias to Sol #3702 history, commit 991009e, later reverted).openaiSupportsNativeMaxEffortcovers the same family), direct OpenAI routes only (the OpenAI fetch wrapper is not applied on passthrough gateways), Responses wire format only.createModel()callers (title generation, advisor streams) never callbuildRequestHeaders, so a provider-level config knob needs a fallback path in the wrapper (or explicit plumbing) to apply there.reasoning: {"effort": "high", "mode": "pro"}completes ongpt-5.6-solwith a plain API key.reasoning.modesupport before building the wire-level workaround.Generated with
mux• Model:anthropic:claude-fable-5• Thinking:high• Cost:$18.71