feat: add Anthropic Claude and Google Gemini provider support

Add handler modules for two new LLM provider APIs, both following the
established pattern from responses.ts: convert inbound request to
ChatCompletionRequest, match fixtures, convert response back to
provider-specific format.

Claude Messages API (/v1/messages):
- Streaming via event: type / data: json SSE format
- Non-streaming JSON responses
- Full message lifecycle: message_start through message_stop
- Tool use with input_json_delta streaming
- msg_ and toolu_ ID prefixes

Google Gemini GenerateContent API:
- /v1beta/models/{model}:generateContent (non-streaming)
- /v1beta/models/{model}:streamGenerateContent (streaming)
- data-only SSE format (no event prefix, no [DONE])
- functionCall/functionResponse round-trips with synthetic IDs
- FUNCTION_CALL finishReason for tool call responses

Also adds generateMessageId() and generateToolUseId() helpers,
server routes for both providers, and comprehensive tests.

src/__tests__/helpers.test.ts

@@ -2,6 +2,8 @@ import { describe, it, expect } from "vitest";
 import {
   generateId,
   generateToolCallId,
+  generateMessageId,
+  generateToolUseId,
   isTextResponse,
   isToolCallResponse,
   isErrorResponse,
@@ -36,6 +38,32 @@ describe("generateToolCallId", () => {
   });
 });
 
+describe("generateMessageId", () => {
+  it("generates message IDs with msg_ prefix", () => {
+    const id = generateMessageId();
+    expect(id).toMatch(/^msg_/);
+    expect(id.length).toBeGreaterThan(5);
+  });
+
+  it("generates unique IDs", () => {
+    const ids = new Set(Array.from({ length: 100 }, () => generateMessageId()));
+    expect(ids.size).toBe(100);
+  });
+});
+
+describe("generateToolUseId", () => {
+  it("generates tool use IDs with toolu_ prefix", () => {
+    const id = generateToolUseId();
+    expect(id).toMatch(/^toolu_/);
+    expect(id.length).toBeGreaterThan(7);
+  });
+
+  it("generates unique IDs", () => {
+    const ids = new Set(Array.from({ length: 100 }, () => generateToolUseId()));
+    expect(ids.size).toBe(100);
+  });
+});
+
 describe("type guards", () => {
   it("isTextResponse identifies text responses", () => {
     expect(isTextResponse({ content: "hello" })).toBe(true);