move pi-mono into companion-cloud as apps/companion-os

- Copy all pi-mono source into apps/companion-os/
- Update Dockerfile to COPY pre-built binary instead of downloading from GitHub Releases
- Update deploy-staging.yml to build pi from source (bun compile) before Docker build
- Add apps/companion-os/** to path triggers
- No more cross-repo dispatch needed

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

packages/ai/test/xhigh.test.ts

@@ -0,0 +1,81 @@
+import { describe, expect, it } from "vitest";
+import { getModel } from "../src/models.js";
+import { stream } from "../src/stream.js";
+import type { Context, Model } from "../src/types.js";
+
+function makeContext(): Context {
+  return {
+    messages: [
+      {
+        role: "user",
+        content: `What is ${(Math.random() * 100) | 0} + ${(Math.random() * 100) | 0}? Think step by step.`,
+        timestamp: Date.now(),
+      },
+    ],
+  };
+}
+
+describe.skipIf(!process.env.OPENAI_API_KEY)("xhigh reasoning", () => {
+  describe("codex-max (supports xhigh)", () => {
+    // Note: codex models only support the responses API, not chat completions
+    it("should work with openai-responses", async () => {
+      const model = getModel("openai", "gpt-5.1-codex-max");
+      const s = stream(model, makeContext(), { reasoningEffort: "xhigh" });
+      let hasThinking = false;
+
+      for await (const event of s) {
+        if (
+          event.type === "thinking_start" ||
+          event.type === "thinking_delta"
+        ) {
+          hasThinking = true;
+        }
+      }
+
+      const response = await s.result();
+      expect(response.stopReason, `Error: ${response.errorMessage}`).toBe(
+        "stop",
+      );
+      expect(response.content.some((b) => b.type === "text")).toBe(true);
+      expect(
+        hasThinking || response.content.some((b) => b.type === "thinking"),
+      ).toBe(true);
+    });
+  });
+
+  describe("gpt-5-mini (does not support xhigh)", () => {
+    it("should error with openai-responses when using xhigh", async () => {
+      const model = getModel("openai", "gpt-5-mini");
+      const s = stream(model, makeContext(), { reasoningEffort: "xhigh" });
+
+      for await (const _ of s) {
+        // drain events
+      }
+
+      const response = await s.result();
+      expect(response.stopReason).toBe("error");
+      expect(response.errorMessage).toContain("xhigh");
+    });
+
+    it("should error with openai-completions when using xhigh", async () => {
+      const { compat: _compat, ...baseModel } = getModel(
+        "openai",
+        "gpt-5-mini",
+      );
+      void _compat;
+      const model: Model<"openai-completions"> = {
+        ...baseModel,
+        api: "openai-completions",
+      };
+      const s = stream(model, makeContext(), { reasoningEffort: "xhigh" });
+
+      for await (const _ of s) {
+        // drain events
+      }
+
+      const response = await s.result();
+      expect(response.stopReason).toBe("error");
+      expect(response.errorMessage).toContain("xhigh");
+    });
+  });
+});