Name the setting and value when a size setting does not parse (closes #429)

A non-numeric chunk_size or blob_size_limit failed with an error that named neither the setting nor the value. Every size setting now fails at load with its name and the quoted value, for example chunk_size: "banana" is not a size; use a number of bytes or a unit such as 10MB. A value too large for a size says so, with the setting name.

Model: opus-5-5

internal/config/size.go

@@ -4,13 +4,20 @@ import (
 	"errors"
 	"fmt"
 	"math"
+	"reflect"
+	"slices"
+	"strconv"
+	"strings"
 
 	"github.com/dustin/go-humanize"
+	"gopkg.in/yaml.v3"
 )
 
 var (
 	errSizeType     = errors.New("size must be a number or string")
 	errSizeTooLarge = errors.New("size exceeds maximum supported value")
+	errNotASize     = errors.New(
+		"is not a size; use a number of bytes or a unit such as 10MB")
 )
 
 // Size represents a byte size that can be specified in configuration files.
@@ -32,6 +39,15 @@ func (s *Size) UnmarshalYAML(unmarshal func(any) error) error {
 		return nil
 	}
 
+	// A number too large for an int64 decodes as a float64. Its text can be
+	// 1e+20, which is not a size string.
+	var floatVal float64
+
+	err = unmarshal(&floatVal)
+	if err == nil && floatVal > math.MaxInt64 {
+		return errSizeTooLarge
+	}
+
 	// Try to unmarshal as string
 	var strVal string
 
@@ -40,17 +56,66 @@ func (s *Size) UnmarshalYAML(unmarshal func(any) error) error {
 		return errSizeType
 	}
 
-	// Parse the string using go-humanize
-	bytes, err := humanize.ParseBytes(strVal)
+	size, err := ParseSize(strVal)
 	if err != nil {
-		return fmt.Errorf("invalid size format: %w", err)
+		return err
 	}
 
-	if bytes > math.MaxInt64 {
-		return fmt.Errorf("%w: %s", errSizeTooLarge, strVal)
+	*s = size
+
+	return nil
+}
+
+// checkSizes returns an error naming the first size setting in node whose
+// value is not a size. node is the config, or the part of it at the dotted
+// keys, after smartconfig has filled in its ${...} references.
+func checkSizes(node *yaml.Node, keys []string) error {
+	typ, err := SettingType(keys)
+	if err != nil {
+		// Unknown keys are refused before this check, so keys is in one of
+		// two places. The env section holds no settings. A value of the
+		// wrong shape, such as a map given for hostname or inside exclude,
+		// is reported later by the YAML decoder.
+		return nil //nolint:nilerr // not an error here
 	}
 
-	*s = Size(bytes)
+	if typ == reflect.TypeFor[Size]() {
+		var size Size
+
+		err = node.Decode(&size)
+		if err != nil {
+			return fmt.Errorf("%s: %w", strings.Join(keys, "."), err)
+		}
+
+		return nil
+	}
+
+	switch node.Kind {
+	case yaml.DocumentNode:
+		for _, child := range node.Content {
+			err = checkSizes(child, keys)
+			if err != nil {
+				return err
+			}
+		}
+	case yaml.MappingNode:
+		for i := 0; i+1 < len(node.Content); i += 2 {
+			err = checkSizes(node.Content[i+1],
+				slices.Concat(keys, []string{node.Content[i].Value}))
+			if err != nil {
+				return err
+			}
+		}
+	case yaml.SequenceNode:
+		for i, child := range node.Content {
+			err = checkSizes(child, slices.Concat(keys, []string{strconv.Itoa(i)}))
+			if err != nil {
+				return err
+			}
+		}
+	case yaml.ScalarNode, yaml.AliasNode:
+		// A scalar holds no settings, and the filled config has no aliases.
+	}
 
 	return nil
 }
@@ -70,16 +135,17 @@ func (s Size) String() string {
 	return humanize.Bytes(uint64(s))
 }
 
-// ParseSize parses a size string into a Size value
+// ParseSize parses a size string, such as "10MB", into a Size value. An
+// error quotes s.
 func ParseSize(s string) (Size, error) {
-	bytes, err := humanize.ParseBytes(s)
+	bytes, err := humanize.ParseBigBytes(s)
 	if err != nil {
-		return 0, fmt.Errorf("invalid size format: %w", err)
+		return 0, fmt.Errorf("%q %w", s, errNotASize)
 	}
 
-	if bytes > math.MaxInt64 {
+	if !bytes.IsInt64() {
 		return 0, fmt.Errorf("%w: %s", errSizeTooLarge, s)
 	}
 
-	return Size(bytes), nil
+	return Size(bytes.Int64()), nil
 }