fix: DeepSeek reasoning_content dropped on multi-step tool calls

- Base URL corrected: zen/v1 -> zen/go/v1 (opencode-go provider)
- Model changed: deepseek-v4-flash-free -> deepseek-v4-flash
- Added wrapLanguageModel middleware to inject reasoning_content via
  providerMetadata.openaiCompatible before each stream call
- Fixed test mocks: removed vi.importActual (unsupported in Bun), added
  tool factory mocks, preserved real tool export in ai mock
- Added 11 tests for the normalizeMessages middleware

1 files changed, 2 insertions, 2 deletions

diff --git a/packages/core/tests/agent/agent.test.ts b/packages/core/tests/agent/agent.test.ts
index 81d42c8..92df90e 100644
--- a/packages/core/tests/agent/agent.test.ts
+++ b/packages/core/tests/agent/agent.test.ts
@@ -4,8 +4,8 @@ import { Agent } from "../../src/agent/agent.js";
 import type { AgentConfig } from "../../src/types/index.js";
 
 // Mock the ai module's streamText
-vi.mock("ai", async (importOriginal) => {
-	const actual = await importOriginal<typeof import("ai")>();
+vi.mock("ai", async () => {
+	const actual = await import("ai");
 	return {
 		...actual,
 		streamText: vi.fn(),