fix: include output tokens in context window usage calculation

Include output tokens from last response in getContextWindowUsage calculation.
Output tokens become part of next request's input (conversation history), so
they must be counted to avoid overestimating remainingTokens. This aligns with
preemptive-compaction's calculation which already includes output tokens correctly.

🤖 GENERATED WITH ASSISTANCE OF [OhMyOpenCode](https://github.com/code-yeongyu/oh-my-opencode)

src/shared/dynamic-truncator.ts

@@ -112,7 +112,10 @@ export async function getContextWindowUsage(
 
     const lastAssistant = assistantMessages[assistantMessages.length - 1]
     const lastTokens = lastAssistant.tokens
-    const usedTokens = (lastTokens?.input ?? 0) + (lastTokens?.cache?.read ?? 0)
+    const usedTokens =
+      (lastTokens?.input ?? 0) +
+      (lastTokens?.cache?.read ?? 0) +
+      (lastTokens?.output ?? 0)
     const remainingTokens = ANTHROPIC_ACTUAL_LIMIT - usedTokens
 
     return {