Switch to AsyncAnthropic client

The sync Anthropic client was blocking the event loop inside async
FastAPI routes. Switch to AsyncAnthropic so the API call properly
yields to the event loop while waiting for the response.

Closes #9

🤖 Generated by LLM (Claude, via OpenClaw)

Author: mattgodbolt-molty

app/explain.py

@@ -1,6 +1,6 @@
 import logging
 
-from anthropic import Anthropic
+from anthropic import AsyncAnthropic
 
 from app.cache import CacheProvider, cache_response, get_cached_response
 from app.explain_api import CostBreakdown, ExplainRequest, ExplainResponse, TokenUsage
@@ -19,7 +19,7 @@
 
 async def process_request(
     body: ExplainRequest,
-    client: Anthropic,
+    client: AsyncAnthropic,
     prompt: Prompt,
     metrics_provider: MetricsProvider,
     cache_provider: CacheProvider | None = None,
@@ -31,7 +31,7 @@ async def process_request(
 
     Args:
         body: The request body as a Pydantic model
-        client: Anthropic client instance
+        client: AsyncAnthropic client instance
         prompt: Prompt instance for generating messages
         metrics_provider: metrics provider for tracking stats
         cache_provider: cache provider for storing/retrieving responses
@@ -69,7 +69,7 @@ async def process_request(
 
 async def _call_anthropic_api(
     body: ExplainRequest,
-    client: Anthropic,
+    client: AsyncAnthropic,
     prompt: Prompt,
     metrics_provider: MetricsProvider,
 ) -> ExplainResponse:
@@ -92,7 +92,7 @@ async def _call_anthropic_api(
     # Call Claude API
     LOGGER.info("Using Anthropic client with model: %s", {prompt_data["model"]})
 
-    message = client.messages.create(
+    message = await client.messages.create(
         model=prompt_data["model"],
         max_tokens=prompt_data["max_tokens"],
         temperature=prompt_data["temperature"],

app/main.py

@@ -2,7 +2,7 @@
 from contextlib import asynccontextmanager
 from pathlib import Path
 
-from anthropic import Anthropic
+from anthropic import AsyncAnthropic
 from anthropic import __version__ as anthropic_version
 from fastapi import FastAPI, Request
 from fastapi.middleware.cors import CORSMiddleware
@@ -42,7 +42,7 @@ async def lifespan(app: FastAPI):
 
     # Store shared resources in app.state
     app.state.settings = settings
-    app.state.anthropic_client = Anthropic(api_key=settings.anthropic_api_key)
+    app.state.anthropic_client = AsyncAnthropic(api_key=settings.anthropic_api_key)
 
     # Load the prompt configuration
     prompt_config_path = Path(__file__).parent / "prompt.yaml"

app/test_explain.py

@@ -1,6 +1,6 @@
 import json
 from pathlib import Path
-from unittest.mock import MagicMock
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
@@ -65,7 +65,7 @@ def mock_anthropic_client():
     mock_message.usage.input_tokens = 100
     mock_message.usage.output_tokens = 50
 
-    mock_client.messages.create.return_value = mock_message
+    mock_client.messages.create = AsyncMock(return_value=mock_message)
     return mock_client