feat: CLI v2.1.68–v2.1.74 compatibility updates (#221)

## Summary

This PR brings Hikari Desktop up to full compatibility with Claude Code CLI versions v2.1.68 through v2.1.74, implementing all changelog items audited in issues #200–#218.

## Changes

### Bug Fixes
- Remove deprecated Claude Opus 4.0 and 4.1 models from the model selector
- Auto-migrate users pinned to deprecated models to Opus 4.6

### New Features
- Add cron tool support (`CronCreate`, `CronDelete`, `CronList`) with character state mapping and `CLAUDE_CODE_DISABLE_CRON` settings toggle
- Handle `EnterWorktree` and `ExitWorktree` tools in character state mapping and tool display
- Add CLI update check with npm registry indicator in the version bar
- Add `agent_type` field and support the Agent tool rename from CLI v2.1.69
- Consume `worktree` field from status line hook events
- Display per-agent model override in the agent monitor tree
- Expose Claude Code CLI built-in slash commands (`/simplify`, `/loop`, `/batch`, `/memory`, `/context`) in the command menu with CLI badges
- Add `includeGitInstructions` toggle in settings
- Add `ENABLE_CLAUDEAI_MCP_SERVERS` opt-out setting
- Linkify MCP binary file paths (PDFs, audio, Office docs) in markdown output
- Add auto-memory panel, `/memory` slash command shortcut, and unified toast notification system
- Toast notifications for `WorktreeCreate` and `WorktreeRemove` hook events
- Sort session resume list by most recent activity, with most recent user message as preview
- Convert WSL Linux paths to Windows UNC paths when opening binary files via `open_binary_file` command
- Expose `autoMemoryDirectory` setting in ConfigSidebar (Agent Settings section)
- Add `/context` as a CLI built-in in the slash command menu
- Expose `modelOverrides` setting as a JSON textarea in ConfigSidebar (for AWS Bedrock, Google Vertex, etc.)

> **Note:** The CLI update check commit does not have a corresponding issue — it was a bonus addition during the audit sprint.

## Closes

Closes #200
Closes #201
Closes #202
Closes #205
Closes #206
Closes #207
Closes #208
Closes #209
Closes #210
Closes #211
Closes #212
Closes #213
Closes #214
Closes #215
Closes #216
Closes #217
Closes #218

Reviewed-on: #221
Co-authored-by: Hikari <hikari@nhcarrigan.com>
Co-committed-by: Hikari <hikari@nhcarrigan.com>

src/lib/commands/slashCommands.test.ts

@@ -65,6 +65,10 @@ vi.mock("$lib/stores/config", () => ({
       use_worktree: false,
       disable_1m_context: false,
       max_output_tokens: null,
+      include_git_instructions: true,
+      enable_claudeai_mcp_servers: true,
+      auto_memory_directory: null,
+      model_overrides: null,
     }),
   },
 }));
@@ -87,10 +91,15 @@ describe("slashCommands", () => {
       expect(commandNames).toContain("search");
       expect(commandNames).toContain("summarise");
       expect(commandNames).toContain("skill");
+      expect(commandNames).toContain("simplify");
+      expect(commandNames).toContain("loop");
+      expect(commandNames).toContain("batch");
+      expect(commandNames).toContain("memory");
+      expect(commandNames).toContain("context");
     });
 
-    it("has 7 commands total", () => {
-      expect(slashCommands.length).toBe(7);
+    it("has 12 commands total", () => {
+      expect(slashCommands.length).toBe(12);
     });
 
     it("each command has required properties", () => {
@@ -160,6 +169,52 @@ describe("slashCommands", () => {
       expect(skillCmd!.description).toBe("Invoke a Claude Code skill from ~/.claude/skills/");
       expect(skillCmd!.usage).toBe("/skill [name] [data]");
     });
+
+    it("simplify command has correct metadata and source", () => {
+      const simplifyCmd = slashCommands.find((cmd) => cmd.name === "simplify");
+      expect(simplifyCmd).toBeDefined();
+      expect(simplifyCmd!.source).toBe("cli");
+      expect(simplifyCmd!.usage).toBe("/simplify");
+    });
+
+    it("loop command has correct metadata and source", () => {
+      const loopCmd = slashCommands.find((cmd) => cmd.name === "loop");
+      expect(loopCmd).toBeDefined();
+      expect(loopCmd!.source).toBe("cli");
+      expect(loopCmd!.usage).toBe("/loop [interval] [command]");
+    });
+
+    it("batch command has correct metadata and source", () => {
+      const batchCmd = slashCommands.find((cmd) => cmd.name === "batch");
+      expect(batchCmd).toBeDefined();
+      expect(batchCmd!.source).toBe("cli");
+      expect(batchCmd!.usage).toBe("/batch [tasks]");
+    });
+
+    it("context command has correct metadata and source", () => {
+      const contextCmd = slashCommands.find((cmd) => cmd.name === "context");
+      expect(contextCmd).toBeDefined();
+      expect(contextCmd!.source).toBe("cli");
+      expect(contextCmd!.usage).toBe("/context");
+    });
+
+    it("app commands do not have source set", () => {
+      const appCommandNames = ["cd", "clear", "new", "help", "search", "summarise", "skill"];
+      appCommandNames.forEach((name) => {
+        const cmd = slashCommands.find((c) => c.name === name);
+        expect(cmd).toBeDefined();
+        expect(cmd!.source).toBeUndefined();
+      });
+    });
+
+    it("cli commands have source set to 'cli'", () => {
+      const cliCommandNames = ["simplify", "loop", "batch", "memory", "context"];
+      cliCommandNames.forEach((name) => {
+        const cmd = slashCommands.find((c) => c.name === name);
+        expect(cmd).toBeDefined();
+        expect(cmd!.source).toBe("cli");
+      });
+    });
   });
 
   describe("parseSlashCommand", () => {
@@ -342,6 +397,19 @@ describe("slashCommands", () => {
       expect(names).toContain("search");
       expect(names).toContain("summarise");
       expect(names).toContain("skill");
+      expect(names).toContain("simplify");
+    });
+
+    it("returns /loop for /l prefix", () => {
+      const result = getMatchingCommands("/l");
+      const names = result.map((cmd) => cmd.name);
+      expect(names).toContain("loop");
+    });
+
+    it("returns /batch for /b prefix", () => {
+      const result = getMatchingCommands("/b");
+      const names = result.map((cmd) => cmd.name);
+      expect(names).toContain("batch");
     });
 
     it("is case insensitive", () => {
@@ -412,6 +480,19 @@ describe("slashCommands", () => {
       expect(testCommand.description).toBe("A test command");
       expect(testCommand.usage).toBe("/test [arg]");
       expect(typeof testCommand.execute).toBe("function");
+      expect(testCommand.source).toBeUndefined();
+    });
+
+    it("can create a cli-sourced slash command object", () => {
+      const cliCommand: SlashCommand = {
+        name: "cli-test",
+        description: "A CLI command",
+        usage: "/cli-test",
+        source: "cli",
+        execute: vi.fn(),
+      };
+
+      expect(cliCommand.source).toBe("cli");
     });
 
     it("execute can be async function", () => {
@@ -715,6 +796,125 @@ describe("slashCommands", () => {
       });
     });
 
+    describe("/simplify execute", () => {
+      it("shows error when no active conversation", async () => {
+        getMock.mockReturnValue(null);
+        const simplifyCmd = slashCommands.find((cmd) => cmd.name === "simplify")!;
+        await simplifyCmd.execute("");
+        expect(claudeStore.addLine).toHaveBeenCalledWith("error", "No active conversation");
+      });
+
+      it("sends /simplify prompt to Claude when there is an active conversation", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const simplifyCmd = slashCommands.find((cmd) => cmd.name === "simplify")!;
+        await simplifyCmd.execute("");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/simplify",
+        });
+      });
+    });
+
+    describe("/loop execute", () => {
+      it("shows error when no active conversation", async () => {
+        getMock.mockReturnValue(null);
+        const loopCmd = slashCommands.find((cmd) => cmd.name === "loop")!;
+        await loopCmd.execute("5m /help");
+        expect(claudeStore.addLine).toHaveBeenCalledWith("error", "No active conversation");
+      });
+
+      it("sends /loop with args when args are provided", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const loopCmd = slashCommands.find((cmd) => cmd.name === "loop")!;
+        await loopCmd.execute("5m /help");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/loop 5m /help",
+        });
+      });
+
+      it("sends /loop without args when no args provided", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const loopCmd = slashCommands.find((cmd) => cmd.name === "loop")!;
+        await loopCmd.execute("");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/loop",
+        });
+      });
+    });
+
+    describe("/batch execute", () => {
+      it("shows error when no active conversation", async () => {
+        getMock.mockReturnValue(null);
+        const batchCmd = slashCommands.find((cmd) => cmd.name === "batch")!;
+        await batchCmd.execute("task1, task2");
+        expect(claudeStore.addLine).toHaveBeenCalledWith("error", "No active conversation");
+      });
+
+      it("sends /batch with args when args are provided", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const batchCmd = slashCommands.find((cmd) => cmd.name === "batch")!;
+        await batchCmd.execute("task1, task2");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/batch task1, task2",
+        });
+      });
+
+      it("sends /batch without args when no args provided", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const batchCmd = slashCommands.find((cmd) => cmd.name === "batch")!;
+        await batchCmd.execute("");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/batch",
+        });
+      });
+    });
+
+    describe("/memory execute", () => {
+      it("opens the memory browser panel without requiring an active conversation", () => {
+        getMock.mockReturnValue(null);
+        const memoryCmd = slashCommands.find((cmd) => cmd.name === "memory")!;
+        memoryCmd.execute("");
+        expect(claudeStore.addLine).not.toHaveBeenCalled();
+        expect(invokeMock).not.toHaveBeenCalledWith("send_prompt", expect.anything());
+      });
+
+      it("does not send a prompt to Claude when executed", () => {
+        getMock.mockReturnValue("conv-123");
+        const memoryCmd = slashCommands.find((cmd) => cmd.name === "memory")!;
+        memoryCmd.execute("");
+        expect(invokeMock).not.toHaveBeenCalledWith("send_prompt", expect.anything());
+      });
+    });
+
+    describe("/context execute", () => {
+      it("shows error when no active conversation", async () => {
+        getMock.mockReturnValue(null);
+        const contextCmd = slashCommands.find((cmd) => cmd.name === "context")!;
+        await contextCmd.execute("");
+        expect(claudeStore.addLine).toHaveBeenCalledWith("error", "No active conversation");
+      });
+
+      it("sends /context prompt to Claude when there is an active conversation", async () => {
+        getMock.mockReturnValue("conv-123");
+        invokeMock.mockResolvedValue(undefined);
+        const contextCmd = slashCommands.find((cmd) => cmd.name === "context")!;
+        await contextCmd.execute("");
+        expect(invokeMock).toHaveBeenCalledWith("send_prompt", {
+          conversationId: "conv-123",
+          message: "/context",
+        });
+      });
+    });
+
     describe("/cd success path", () => {
       beforeEach(() => {
         vi.useFakeTimers();