feat(fable-mcp): implement FableClient, all tool modules, and server.py

- client.py: async httpx wrapper, FableAPIError, stream_get() SSE generator,
  singleton init_client()/get_client() and _reset_client() for tests
- tools/: notes, tasks, projects, milestones, search, chat — thin async
  functions that accept FableClient and call Fable REST endpoints
- server.py: FastMCP entry point with 20 tools registered via @mcp.tool(),
  each opening a fresh FableClient context per call; validates env vars at startup
- tests: 34 tests covering client HTTP behaviour, error handling, singleton,
  SSE streaming, and all tool modules

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

fable-mcp/fable_mcp/tools/search.py

@@ -0,0 +1,30 @@
+"""MCP tool for semantic search across Fable notes and tasks."""
+from __future__ import annotations
+
+from typing import Any
+
+from fable_mcp.client import FableClient
+
+
+async def search(
+    client: FableClient,
+    *,
+    q: str,
+    content_type: str = "all",
+    limit: int = 10,
+) -> dict[str, Any]:
+    """Semantic search over notes and/or tasks.
+
+    Args:
+        q: Search query string.
+        content_type: One of "note", "task", or "all" (default).
+        limit: Maximum number of results to return.
+
+    Returns:
+        Dict with "results" list and "total" count.
+        Each result has: id, title, body, is_task, tags, similarity.
+    """
+    params: dict[str, Any] = {"q": q, "limit": limit}
+    if content_type != "all":
+        params["content_type"] = content_type
+    return await client.get("/api/search", params=params)