feat(ai): add reasoning token counts to Usage

Add optional reasoning?: number to Usage as a subset of output. Populate
for Anthropic (output_tokens_details.thinking_tokens), OpenAI
Responses/Codex/Azure (output_tokens_details.reasoning_tokens), OpenAI
Completions (completion_tokens_details.reasoning_tokens), and Google
Generative AI / Vertex (thoughtsTokenCount). Bedrock Converse and Mistral
do not return a reasoning breakdown, so they stay unset.

closes #6057

packages/ai/src/api/openai-responses-shared.ts

@@ -312,6 +312,7 @@ export async function processResponsesStream<TApi extends Api>(
 				output: response.usage.output_tokens || 0,
 				cacheRead: cachedTokens,
 				cacheWrite: 0,
+				reasoning: response.usage.output_tokens_details?.reasoning_tokens || 0,
 				totalTokens: response.usage.total_tokens || 0,
 				cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 },
 			};