fix: add retry with exponential backoff for API calls (issue #9)

- Retry up to 3 times with exponential backoff (2s base delay)
- Retries on 5xx errors, timeouts, and connection errors
- Configurable via CLOVER_MAX_RETRIES and CLOVER_RETRY_BASE_DELAY
- Logs retry attempts with delay and attempt number

config/settings.py

@@ -43,6 +43,8 @@ def load_config():
         "project_root": os.getenv("CLOVER_PROJECT_ROOT", "."),
         "summary_file": os.getenv("CLOVER_SUMMARY_FILE", "clover.md"),
         "structure_file": os.getenv("CLOVER_STRUCTURE_FILE", "structure.md"),
+        "max_retries": int(os.getenv("CLOVER_MAX_RETRIES", "3")),
+        "retry_base_delay": float(os.getenv("CLOVER_RETRY_BASE_DELAY", "2")),
     }
 
     # Debug output if enabled

models/api_client.py

@@ -5,6 +5,7 @@ Handles communication with the OpenAI-compatible LLM server
 
 import json
 import os
+import time
 from typing import Any, Dict, Optional
 
 import requests
@@ -27,7 +28,10 @@ class APIClient:
         self, endpoint: str, method: str = "GET", data: Optional[Dict] = None
     ) -> Dict[str, Any]:
         """
-        Make a request to the LLM API server
+        Make a request to the LLM API server with retry and exponential backoff.
+
+        Retries up to 3 times with exponential backoff (2s base delay) for
+        transient failures (5xx errors, connection errors, timeouts).
 
         Args:
             endpoint (str): API endpoint
@@ -37,6 +41,12 @@ class APIClient:
         Returns:
             dict: Response from the API
         """
+        max_retries = self.config.get("max_retries", 3)
+        base_delay = self.config.get("retry_base_delay", 2)
+
+        last_exception = None
+
+        for attempt in range(max_retries + 1):
             try:
                 # Ensure base_url doesn't have trailing slash and endpoint has leading slash
                 base = self.base_url.rstrip("/")
@@ -55,7 +65,9 @@ class APIClient:
 
                 if method == "GET":
                     response = requests.get(
-                    url, headers=headers, timeout=self.config.get("timeout", 300)
+                        url,
+                        headers=headers,
+                        timeout=self.config.get("timeout", 300),
                     )
                 elif method == "POST":
                     response = requests.post(
@@ -67,9 +79,41 @@ class APIClient:
                 else:
                     raise ValueError(f"Unsupported HTTP method: {method}")
 
+                # Retry on 5xx server errors
+                if response.status_code >= 500 and attempt < max_retries:
+                    delay = base_delay * (2**attempt)
+                    print(
+                        f"Server error {response.status_code}, "
+                        f"retrying in {delay}s (attempt {attempt + 1}/{max_retries})"
+                    )
+                    time.sleep(delay)
+                    continue
+
                 response.raise_for_status()
                 return {"success": True, "data": response.json()}
 
+            except requests.exceptions.Timeout as e:
+                last_exception = e
+                if attempt < max_retries:
+                    delay = base_delay * (2**attempt)
+                    print(
+                        f"Timeout, retrying in {delay}s "
+                        f"(attempt {attempt + 1}/{max_retries})"
+                    )
+                    time.sleep(delay)
+                    continue
+
+            except requests.exceptions.ConnectionError as e:
+                last_exception = e
+                if attempt < max_retries:
+                    delay = base_delay * (2**attempt)
+                    print(
+                        f"Connection error, retrying in {delay}s "
+                        f"(attempt {attempt + 1}/{max_retries})"
+                    )
+                    time.sleep(delay)
+                    continue
+
             except requests.exceptions.RequestException as e:
                 return {"success": False, "error": f"HTTP Request failed: {str(e)}"}
             except json.JSONDecodeError as e:
@@ -77,6 +121,14 @@ class APIClient:
             except Exception as e:
                 return {"success": False, "error": f"Unexpected error: {str(e)}"}
 
+        # All retries exhausted
+        if last_exception:
+            return {
+                "success": False,
+                "error": f"Request failed after {max_retries} retries: {str(last_exception)}",
+            }
+        return {"success": False, "error": "Request failed after maximum retries"}
+
     def list_models(self) -> Dict[str, Any]:
         """
         Get list of available models from the LLM server