fix(models): preserve user reasoning override when merging with built-in catalog

When a built-in provider model has reasoning:true (e.g. MiniMax-M2.5) and
the user explicitly sets reasoning:false in their config, mergeProviderModels
unconditionally overwrote the user's value with the built-in catalog value.

The merge code refreshes capability metadata (input, contextWindow, maxTokens,
reasoning) from the implicit catalog. This is correct for fields like
contextWindow and maxTokens — the catalog has authoritative values that
shouldn't be stale. But reasoning is a user preference, not just a
capability descriptor: users may need to disable it to avoid 'Message
ordering conflict' errors with certain models or backends.

Fix: check whether 'reasoning' is present in the explicit (user-supplied)
model entry. If the user has set it (even to false), honour that value.
If the user hasn't set it, fall back to the built-in catalog default.

This allows users to configure tools.models.providers.minimax.models with
reasoning:false for MiniMax-M2.5 without being silently overridden.

Fixes #25244

src/agents/models-config.ts

@@ -47,10 +47,14 @@ function mergeProviderModels(implicit: ProviderConfig, explicit: ProviderConfig)
 
     // Refresh capability metadata from the implicit catalog while preserving
     // user-specific fields (cost, headers, compat, etc.) on explicit entries.
+    // reasoning is treated as user-overridable: if the user has explicitly set
+    // it in their config (key present), honour that value; otherwise fall back
+    // to the built-in catalog default so new reasoning models work out of the
+    // box without requiring every user to configure it.
     return {
       ...explicitModel,
       input: implicitModel.input,
-      reasoning: implicitModel.reasoning,
+      reasoning: "reasoning" in explicitModel ? explicitModel.reasoning : implicitModel.reasoning,
       contextWindow: implicitModel.contextWindow,
       maxTokens: implicitModel.maxTokens,
     };