Fix retry patterns

README.md

@@ -37,15 +37,52 @@ Therefore, I present you the simple client to which you can copy & paste your gr
 * `GRAPHQL_CACHE_TTL` -  Cache TTL in seconds for SELECT type of queries. Default: `5`
 * `GRAPHQL_OUTPUT` - Output format. Default: `string`, available: `byte`, `string`, `mapstring`
 * `LOG_LEVEL` - Logging level. Default: `info` available: `debug`, `info`, `warn`, `error`
-* `GRAPHQL_RETRIES_ENABLE` - Should retries be enabled? Default: `true`
-* `GRAPHQL_RETRIES_NUMBER` - Number of retries: Default: `1`
+* `GRAPHQL_RETRIES_ENABLE` - Should retries be enabled? Default: `false`
+* `GRAPHQL_RETRIES_NUMBER` - Number of retries: Default: `3`
 * `GRAPHQL_RETRIES_DELAY` - Delay in retries in milliseconds. Default: `250`
+* `GRAPHQL_RETRIES_PATTERNS` - Comma-separated error patterns that trigger retries. Default: `postgres,connection,timeout,transaction,could not,temporarily unavailable,deadlock`
 
 ### Modifiers on the fly
 
 * `gql.SetEndpoint('your-endpoint-url')` - modifies endpoint, without the need to set the environment variable
 * `gql.SetOutput('byte')` - modifies output format, without the need to set the environment variable
 
+### Retries
+
+The library supports automatic retries for both HTTP-level errors and GraphQL errors that match configurable patterns.
+
+**Retry behavior:**
+- **HTTP errors** (status codes outside 200-299): Always retried if retries are enabled
+- **GraphQL errors**: Only retried if the error message contains one of the configured patterns
+- **Non-matching errors**: Fail immediately without retrying (e.g., validation errors, field not found)
+
+**Configuring retryable patterns:**
+
+By default, errors containing these patterns will trigger retries:
+- `postgres` - Database connection/transaction errors
+- `connection` - Network connection issues
+- `timeout` - Request timeout errors
+- `transaction` - Database transaction conflicts
+- `could not` - Generic transient failures
+- `temporarily unavailable` - Service unavailability
+- `deadlock` - Database deadlocks
+
+You can customize these patterns using the `GRAPHQL_RETRIES_PATTERNS` environment variable:
+
+```bash
+export GRAPHQL_RETRIES_PATTERNS="postgres,connection,timeout,custom-error-pattern"
+```
+
+**Example:** To handle flaky Hasura database connections, enable retries:
+
+```bash
+export GRAPHQL_RETRIES_ENABLE=true
+export GRAPHQL_RETRIES_NUMBER=3
+export GRAPHQL_RETRIES_DELAY=250
+```
+
+This will retry GraphQL queries up to 3 times when postgres transaction errors occur, with exponential backoff starting at 250ms.
+
 ### Cache
 
 You have two options to enable the cache:

execute_query.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"strings"
 	"time"
 	"unicode/utf8"
 
@@ -32,6 +33,47 @@ func max(a, b int) int {
 	return b
 }
 
+// isRetryableError checks if GraphQL errors contain patterns that indicate a transient failure
+// that should be retried (e.g., database connection issues, timeouts, transaction conflicts)
+func isRetryableError(errors []struct {
+	Message interface{} `json:"message"`
+}, patterns []string) bool {
+	if len(errors) == 0 || len(patterns) == 0 {
+		return false
+	}
+
+	for _, err := range errors {
+		// Try to extract error message as string
+		var msgStr string
+		switch msg := err.Message.(type) {
+		case string:
+			msgStr = msg
+		case map[string]interface{}:
+			// Handle nested error structures (e.g., {"message": "...", "extensions": {...}})
+			if nestedMsg, ok := msg["message"].(string); ok {
+				msgStr = nestedMsg
+			}
+		default:
+			// If we can't convert to string, try fmt.Sprint as fallback
+			msgStr = fmt.Sprint(msg)
+		}
+
+		if msgStr == "" {
+			continue
+		}
+
+		// Check if error message contains any of the configured retry patterns (case-insensitive)
+		msgLower := strings.ToLower(msgStr)
+		for _, pattern := range patterns {
+			if strings.Contains(msgLower, strings.ToLower(pattern)) {
+				return true
+			}
+		}
+	}
+
+	return false
+}
+
 var (
 	// Shared HTTP transport with optimized settings
 	defaultTransport = &http.Transport{
@@ -331,6 +373,38 @@ func (qe *QueryExecutor) executeQuery() ([]byte, error) {
 				return fmt.Errorf("error unmarshalling HTTP response: %w", err)
 			}
 
+			// Check for GraphQL errors in the response
+			if len(queryResult.Errors) > 0 {
+				// Determine if this is a retryable error based on configured patterns
+				if isRetryableError(queryResult.Errors, qe.retries_patterns) {
+					// Log as warning since we'll retry
+					qe.Logger.Warning(&libpack_logger.LogMessage{
+						Message: "Retryable GraphQL error detected",
+						Pairs:   map[string]interface{}{"errors": queryResult.Errors},
+					})
+					// Return error to trigger retry mechanism
+					return fmt.Errorf("retryable error executing query: %s", queryResult.Errors)
+				}
+
+				// Non-retryable error - log and fail immediately without retrying
+				qe.Logger.Error(&libpack_logger.LogMessage{
+					Message: "Non-retryable GraphQL error",
+					Pairs:   map[string]interface{}{"errors": queryResult.Errors},
+				})
+				// Use retry.Unrecoverable to skip remaining retry attempts
+				return retry.Unrecoverable(fmt.Errorf("error executing query: %s", queryResult.Errors))
+			}
+
+			// Check for null data in the response
+			if queryResult.Data == nil {
+				qe.Logger.Error(&libpack_logger.LogMessage{
+					Message: "GraphQL query returned no data",
+					Pairs:   map[string]interface{}{"error": "data field is null"},
+				})
+				// Null data is typically not retryable (indicates query structure issue)
+				return retry.Unrecoverable(errors.New("error executing query: no data"))
+			}
+
 			return nil
 		},
 		retry.OnRetry(func(n uint, err error) {
@@ -346,33 +420,18 @@ func (qe *QueryExecutor) executeQuery() ([]byte, error) {
 		retry.LastErrorOnly(true),
 	)
 	if err != nil {
-		qe.Logger.Debug(&libpack_logger.LogMessage{
-			Message: "Error executing HTTP request",
+		qe.Logger.Error(&libpack_logger.LogMessage{
+			Message: "Query execution failed after retries",
 			Pairs:   map[string]interface{}{"error": err.Error()},
 		})
 		return nil, err
 	}
 
-	if len(queryResult.Errors) > 0 {
-		qe.Logger.Debug(&libpack_logger.LogMessage{
-			Message: "Error executing query",
-			Pairs:   map[string]interface{}{"error": queryResult.Errors},
-		})
-		return nil, fmt.Errorf("error executing query: %s", queryResult.Errors)
-	}
-
-	if queryResult.Data == nil {
-		qe.Logger.Debug(&libpack_logger.LogMessage{
-			Message: "Error executing query",
-			Pairs:   map[string]interface{}{"error": "no data"},
-		})
-		return nil, errors.New("error executing query: no data")
-	}
-
+	// At this point, we have successfully executed the query and validated the response
 	// Marshal queryResult.Data
 	jsonData, err := json.Marshal(queryResult.Data)
 	if err != nil {
-		qe.Logger.Debug(&libpack_logger.LogMessage{
+		qe.Logger.Error(&libpack_logger.LogMessage{
 			Message: "Error marshalling query result",
 			Pairs:   map[string]interface{}{"error": err.Error(), "data": queryResult.Data},
 		})

main.go

@@ -2,6 +2,7 @@ package gql
 
 import (
 	"net/http"
+	"strings"
 	"time"
 
 	"github.com/gookit/goutil/envutil"
@@ -9,6 +10,22 @@ import (
 	logging "github.com/lukaszraczylo/go-simple-graphql/logging"
 )
 
+// parseRetryPatterns parses a comma-separated string of retry patterns into a slice
+func parseRetryPatterns(patterns string) []string {
+	if patterns == "" {
+		return []string{}
+	}
+	parts := strings.Split(patterns, ",")
+	result := make([]string, 0, len(parts))
+	for _, p := range parts {
+		trimmed := strings.TrimSpace(p)
+		if trimmed != "" {
+			result = append(result, trimmed)
+		}
+	}
+	return result
+}
+
 func NewConnection() (b *BaseClient) {
 	// Read LOG_LEVEL environment variable
 	logLevelStr := envutil.Getenv("LOG_LEVEL", "info")
@@ -38,6 +55,7 @@ func NewConnection() (b *BaseClient) {
 		retries_enable:   envutil.GetBool("GRAPHQL_RETRIES_ENABLE", false),
 		retries_delay:    time.Duration(envutil.GetInt("GRAPHQL_RETRIES_DELAY", 250) * int(time.Millisecond)),
 		retries_number:   envutil.GetInt("GRAPHQL_RETRIES_NUMBER", 3),
+		retries_patterns: parseRetryPatterns(envutil.Getenv("GRAPHQL_RETRIES_PATTERNS", "postgres,connection,timeout,transaction,could not,temporarily unavailable,deadlock")),
 		minify_queries:   envutil.GetBool("GRAPHQL_MINIFY_QUERIES", true), // Default: enabled for production efficiency
 	}
 	b.client = b.createHttpClient()

structs.go

@@ -16,6 +16,7 @@ type BaseClient struct {
 	responseType     string
 	retries_delay    time.Duration
 	retries_number   int
+	retries_patterns []string // Error patterns that should trigger retries
 	MaxGoRoutines    int
 	cache_global     bool
 	retries_enable   bool