Fix Roo provider thinking logic

[mrubens]

No setting for this one

---

Important

Simplifies getRooReasoning() logic by removing unnecessary enableReasoningEffort check in reasoning.ts.

• Behavior:
  • Removes check for enableReasoningEffort === false in getRooReasoning() in reasoning.ts.
  • Now, if reasoningEffort is provided and not "minimal", returns { enabled: true, effort: reasoningEffort }.
  • If reasoningEffort is undefined, returns { enabled: false }.
• Misc:
  • Simplifies logic by removing unnecessary condition in getRooReasoning().

^{This description was created by for 699ffbd. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

Issues Found

• Removed enableReasoningEffort check breaks user settings - The deleted code block (lines 57-62) was necessary to respect when users explicitly disable reasoning via enableReasoningEffort: false. Without this check, the function ignores this setting and may enable reasoning anyway, creating inconsistency with other providers and breaking the existing test at line 774-792.

Follow Along on Roo Code Cloud

[roomote]

Removing this check breaks the enableReasoningEffort setting for the Roo provider. When a user explicitly sets enableReasoningEffort: false in their settings, the function should return { enabled: false } to respect their preference, but now it will ignore this setting and potentially enable reasoning anyway if reasoningEffort has a value. This creates inconsistency with other providers (getOpenRouterReasoning, getAnthropicReasoning, getOpenAiReasoning) which all respect enableReasoningEffort: false via shouldUseReasoningEffort(). The existing test at line 774-792 expects this behavior and will fail without this check.

[roomote]

Review complete. Found 1 issue that needs to be addressed before approval.