fix(kiro): improve direct session cache reuse

Reshape Kiro direct requests so resumed client sessions reuse Kiro's
cache-affinity fields instead of starting unrelated CodeWhisperer
conversations.

- keep conversationState.conversationId stable when the client sends an
  explicit session id (x-session-id, session_id, conversation_id, Claude
  Code session metadata)
- add a stable conversationState.agentContinuationId per Kiro session
- send conversationState.agentTaskType: "vibe" and agentMode: "vibe",
  matching the normal Kiro CLI/KAS chat path
- move Kiro thinking instructions into Kiro-compatible systemPrompt /
  additionalModelRequestFields instead of generic top-level thinking
- keep volatile timestamp context out of the top-level systemPrompt; it
  remains only in user content fallback
- suppress additionalModelRequestFields for legacy 4.5-era Claude/Kiro
  models that reject it, while defaulting future Claude/Kiro model ids
  to supported
- preserve Kiro meteringEvent credit usage internally for accounting
  without leaking provider-specific fields into OpenAI-compatible usage
- prevent unrelated headerless Kiro requests from sharing one
  connection-wide continuation
- cap/evict continuation sessions so long-running processes do not grow
  the continuation map unbounded
- treat generated headerless Kiro sessions as one-shot so they do not
  evict real explicit-session continuations
- keep credit-only Kiro metering valid for internal persistence when
  token metrics are unavailable

tests/unit/kiro-thinking-strip.test.js

@@ -1,5 +1,6 @@
 import { describe, it, expect } from "vitest";
 import { KiroExecutor } from "../../open-sse/executors/kiro.js";
+import "../translator/registerAll.js";
 
 function createMockFrame(eventType, payloadObj) {
   const payloadStr = JSON.stringify(payloadObj);
@@ -47,6 +48,13 @@ async function readAllSSE(stream) {
   return result;
 }
 
+async function readNextWithTimeout(reader) {
+  return Promise.race([
+    reader.read(),
+    new Promise((_, reject) => setTimeout(() => reject(new Error("timed out waiting for SSE chunk")), 100)),
+  ]);
+}
+
 describe("KiroExecutor thinking tag stripping", () => {
   it("strips <thinking> tags from assistantResponseEvent", async () => {
     const executor = new KiroExecutor();
@@ -121,4 +129,53 @@ describe("KiroExecutor thinking tag stripping", () => {
     const contentChunks = objects.filter(obj => obj.choices[0].delta.content !== undefined);
     expect(contentChunks.length).toBe(0);
   });
+
+  it("emits a terminal chunk at messageStop before the upstream stream closes", async () => {
+    const executor = new KiroExecutor();
+
+    const f1 = createMockFrame("assistantResponseEvent", { content: "OK" });
+    const f2 = createMockFrame("messageStopEvent", {});
+
+    const readableStream = new ReadableStream({
+      start(controller) {
+        controller.enqueue(f1);
+        controller.enqueue(f2);
+      }
+    });
+
+    const transformedResponse = executor.transformEventStreamToSSE({ body: readableStream }, "claude-test");
+    const reader = transformedResponse.body.getReader();
+    const decoder = new TextDecoder();
+    let output = "";
+    for (let i = 0; i < 4 && !output.includes("\"finish_reason\":\"stop\""); i++) {
+      const { value } = await readNextWithTimeout(reader);
+      output += decoder.decode(value, { stream: true });
+    }
+    await reader.cancel();
+
+    expect(output).toContain("\"finish_reason\":\"stop\"");
+  });
+
+  it("uses tool_calls finish reason for tool streams without messageStop", async () => {
+    const executor = new KiroExecutor();
+
+    const f1 = createMockFrame("toolUseEvent", { toolUseId: "tool-1", name: "read_file", input: { path: "a.txt" } });
+
+    const readableStream = new ReadableStream({
+      start(controller) {
+        controller.enqueue(f1);
+        controller.close();
+      }
+    });
+
+    const transformedResponse = executor.transformEventStreamToSSE({ body: readableStream }, "claude-test");
+    const output = await readAllSSE(transformedResponse.body);
+    const objects = output
+      .split("\n")
+      .filter(line => line.startsWith("data: ") && !line.includes("[DONE]"))
+      .map(line => JSON.parse(line.slice(6)));
+
+    const finalChunk = objects.at(-1);
+    expect(finalChunk.choices[0].finish_reason).toBe("tool_calls");
+  });
 });