Merge branch 'master' into dev

# Conflicts:
#	src/app/(dashboard)/dashboard/cli-tools/[toolId]/ToolDetailClient.js
#	src/app/(dashboard)/dashboard/cli-tools/components/index.js
#	src/app/(dashboard)/dashboard/providers/[id]/AddApiKeyModal.js
#	src/app/api/cli-tools/all-statuses/route.js
#	src/app/api/settings/route.js
#	src/app/api/v1/models/route.js
#	src/shared/constants/cliTools.js

tests/translator/__snapshots__/golden-request.test.js.snap

@@ -118,6 +118,9 @@ exports[`GOLDEN request: OpenAI → Claude > reasoning_effort → adaptive outpu
       "type": "text",
     },
   ],
+  "thinking": {
+    "type": "adaptive",
+  },
 }
 `;
 

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

@@ -6,8 +6,8 @@ import "./registerAll.js";
 import { translateRequest, translateResponse } from "../../open-sse/translator/index.js";
 import { FORMATS } from "../../open-sse/translator/formats.js";
 
-const C2K = (body) =>
-  translateRequest(FORMATS.CLAUDE, FORMATS.KIRO, "claude-sonnet-4.5", body, true, null, "kiro");
+const C2K = (body, credentials = null, model = "claude-sonnet-4.5") =>
+  translateRequest(FORMATS.CLAUDE, FORMATS.KIRO, model, body, true, credentials, "kiro");
 
 describe("Claude → Kiro (direct route)", () => {
   it("produces a Kiro conversationState payload", () => {
@@ -16,6 +16,27 @@ describe("Claude → Kiro (direct route)", () => {
     expect(out.conversationState.currentMessage.userInputMessage.content).toContain("hello");
   });
 
+  it("keeps conversationId stable from client session headers and replays frozen msg0", () => {
+    const credentials = {
+      rawHeaders: { "x-session-id": "hermes-session-123-claude-replay" },
+      connectionId: "kiro-account-1",
+    };
+    const first = C2K({ messages: [{ role: "user", content: "first" }] }, credentials);
+    const second = C2K({ messages: [{ role: "user", content: "second" }] }, credentials);
+
+    expect(first.conversationState.conversationId).toBe("hermes-session-123-claude-replay");
+    expect(second.conversationState.conversationId).toBe("hermes-session-123-claude-replay");
+    expect(first.conversationState.agentContinuationId).toBeTruthy();
+    expect(second.conversationState.agentContinuationId).toBe(first.conversationState.agentContinuationId);
+    expect(first.conversationState.agentTaskType).toBe("vibe");
+    expect(second.conversationState.history[0].userInputMessage.content).toBe(
+      first.conversationState.currentMessage.userInputMessage.content
+    );
+    expect(second.conversationState.history[0].userInputMessage.modelId).toBe("claude-sonnet-4.5");
+    expect(second.conversationState.currentMessage.userInputMessage.content).toContain("Current time");
+    expect(second.conversationState.currentMessage.userInputMessage.content).toContain("second");
+  });
+
   it("guard 1: with no tools, a dangling tool_result is flattened to text (no structured ref)", () => {
     // Client omitted `tools` but kept a tool_result after compaction.
     const out = C2K({
@@ -60,20 +81,60 @@ describe("Claude → Kiro (direct route)", () => {
       null,
       "kiro"
     );
-    expect(out.conversationState.currentMessage.userInputMessage.content).toContain(
+    expect(out.systemPrompt).toContain(
       "<thinking_mode>enabled</thinking_mode>"
     );
+    expect(out.agentMode).toBe("vibe");
   });
 
-  it("maps output_config.effort high to Kiro max_thinking_length 24576", () => {
+  it("does not send additionalModelRequestFields for Kiro models without effort support", () => {
     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>"
-    );
+    expect(out.additionalModelRequestFields).toBeUndefined();
+    expect(out.thinking).toBeUndefined();
+    expect(out.systemPrompt).toContain("<max_thinking_length>24576</max_thinking_length>");
+  });
+
+  it("maps output_config.effort high to Kiro CLI-style additionalModelRequestFields for effort models", () => {
+    const out = C2K({
+      output_config: { effort: "high" },
+      messages: [{ role: "user", content: "think with adaptive effort" }],
+    }, null, "claude-sonnet-5");
+
+    expect(out.additionalModelRequestFields).toEqual({
+      thinking: { type: "adaptive", display: "summarized" },
+      output_config: { effort: "high" },
+    });
+    expect(out.thinking).toBeUndefined();
+    expect(out.systemPrompt).toContain("<max_thinking_length>24576</max_thinking_length>");
+  });
+
+  it("sends Claude system as top-level systemPrompt and keeps a user-content fallback", () => {
+    const out = C2K({
+      system: "system-only instruction",
+      messages: [{ role: "user", content: "hello" }],
+    });
+
+    expect(out.systemPrompt).toContain("system-only instruction");
+    expect(out.conversationState.currentMessage.userInputMessage.content).toContain("system-only instruction");
+  });
+
+  it("keeps top-level systemPrompt stable across turns", () => {
+    const first = C2K({
+      system: "stable instruction",
+      messages: [{ role: "user", content: "first" }],
+    });
+    const second = C2K({
+      system: "stable instruction",
+      messages: [{ role: "user", content: "second" }],
+    });
+
+    expect(first.systemPrompt).toBe(second.systemPrompt);
+    expect(first.systemPrompt).not.toContain("Current time");
+    expect(first.conversationState.currentMessage.userInputMessage.content).toContain("Current time");
   });
 });
 

tests/translator/thinking-unified.test.js

@@ -55,10 +55,14 @@ describe("extractThinking", () => {
 });
 
 describe("applyThinking per provider format", () => {
-  it("claude 4.6+ → adaptive output_config (no budget_tokens)", () => {
+  it("claude 4.6+ → adaptive thinking + output_config (no budget_tokens)", () => {
     const out = apply("claude", "claude-opus-4.7", { reasoning_effort: "high" }, "claude");
     expect(out.output_config).toEqual({ effort: "high" });
-    expect(out.thinking).toBeUndefined();
+    // Anthropic: on Opus 4.6/4.7/4.8 and Sonnet 4.6 thinking stays OFF unless
+    // thinking:{type:"adaptive"} is sent explicitly; output_config alone is not
+    // enough (and Anthropic-compatible shims like Copilot default off even on
+    // Sonnet 5). Both fields together are the documented adaptive shape.
+    expect(out.thinking).toEqual({ type: "adaptive" });
   });
   it("claude haiku → enabled+budget", () => {
     const out = apply("claude", "claude-haiku-4.5", { reasoning_effort: "high" }, "claude");