fix(kiro): honor thinking effort budgets

Resolve the Kiro thinking budget from client intent (OpenAI reasoning_effort,
OpenAI Responses reasoning.effort, Claude output_config.effort, and Claude
thinking.budget_tokens) by reusing the shared thinkingUnified extractThinking
parser, then inject the resolved budget into the Kiro thinking system prefix.
Explicit none/off/disabled stops the prefix injection; synthetic -thinking
aliases keep the default budget.

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/translator/claude-kiro-direct.test.js

@@ -64,6 +64,17 @@ describe("Claude → Kiro (direct route)", () => {
       "<thinking_mode>enabled</thinking_mode>"
     );
   });
+
+  it("maps output_config.effort high to Kiro max_thinking_length 24576", () => {
+    const out = C2K({
+      output_config: { effort: "high" },
+      messages: [{ role: "user", content: "think with adaptive effort" }],
+    });
+
+    expect(out.conversationState.currentMessage.userInputMessage.content).toContain(
+      "<max_thinking_length>24576</max_thinking_length>"
+    );
+  });
 });
 
 describe("Kiro → Claude (direct route, OpenAI-shaped chunks from executor)", () => {