Add internal structured provider error parsing

This commit is contained in:
2026-08-23 18:54:42 +00:00
parent 5fff8cd623
commit af0bd3f31a
4 changed files with 979 additions and 50 deletions

View File

@@ -0,0 +1,173 @@
package llm
import (
"encoding/json"
"errors"
"fmt"
"io"
"strings"
"unicode"
)
const (
maxProviderErrorResponseBytes int64 = 64 << 10
maxProviderErrorIdentifierRunes = 256
maxProviderErrorMessageRunes = 4096
)
// ProviderHTTPError describes a non-success response from an LLM provider.
type ProviderHTTPError struct {
statusCode int
providerCode string
providerType string
providerMessage string
}
func (e *ProviderHTTPError) StatusCode() int {
if e == nil {
return 0
}
return e.statusCode
}
func (e *ProviderHTTPError) ProviderCode() string {
if e == nil {
return ""
}
return e.providerCode
}
func (e *ProviderHTTPError) ProviderType() string {
if e == nil {
return ""
}
return e.providerType
}
func (e *ProviderHTTPError) ProviderMessage() string {
if e == nil {
return ""
}
return e.providerMessage
}
func (e *ProviderHTTPError) Error() string {
if e == nil || e.statusCode == 0 {
return ErrUnexpectedStatus.Error()
}
return fmt.Sprintf("%s: status=%d", ErrUnexpectedStatus, e.statusCode)
}
func (e *ProviderHTTPError) GoString() string {
return e.Error()
}
func (e *ProviderHTTPError) Unwrap() error {
return ErrUnexpectedStatus
}
type providerErrorDetails struct {
providerCode string
providerType string
providerMessage string
}
func newProviderHTTPError(statusCode int, details providerErrorDetails) *ProviderHTTPError {
return &ProviderHTTPError{
statusCode: statusCode,
providerCode: details.providerCode,
providerType: details.providerType,
providerMessage: details.providerMessage,
}
}
func parseProviderErrorEnvelope(body []byte) providerErrorDetails {
decoder := json.NewDecoder(strings.NewReader(string(body)))
decoder.UseNumber()
var envelope map[string]json.RawMessage
if err := decoder.Decode(&envelope); err != nil {
return providerErrorDetails{}
}
var trailing any
if err := decoder.Decode(&trailing); !errors.Is(err, io.EOF) {
return providerErrorDetails{}
}
rawError, ok := envelope["error"]
if !ok {
return providerErrorDetails{}
}
var providerError map[string]json.RawMessage
if err := json.Unmarshal(rawError, &providerError); err != nil || providerError == nil {
return providerErrorDetails{}
}
var details providerErrorDetails
if raw, ok := providerError["message"]; ok {
var value string
if json.Unmarshal(raw, &value) == nil {
details.providerMessage = normalizeProviderErrorMessage(value)
}
}
if raw, ok := providerError["type"]; ok {
var value string
if json.Unmarshal(raw, &value) == nil {
details.providerType = normalizeProviderErrorIdentifier(value)
}
}
if raw, ok := providerError["code"]; ok {
var value any
fieldDecoder := json.NewDecoder(strings.NewReader(string(raw)))
fieldDecoder.UseNumber()
if fieldDecoder.Decode(&value) == nil {
switch value := value.(type) {
case string:
details.providerCode = normalizeProviderErrorIdentifier(value)
case json.Number:
details.providerCode = normalizeProviderErrorIdentifier(value.String())
}
}
}
return details
}
func normalizeProviderErrorIdentifier(value string) string {
normalized := normalizeProviderErrorText(value)
if len([]rune(normalized)) > maxProviderErrorIdentifierRunes {
return ""
}
return normalized
}
func normalizeProviderErrorMessage(value string) string {
normalized := normalizeProviderErrorText(value)
runes := []rune(normalized)
if len(runes) <= maxProviderErrorMessageRunes {
return normalized
}
return string(runes[:maxProviderErrorMessageRunes-1]) + "…"
}
func normalizeProviderErrorText(value string) string {
value = strings.ToValidUTF8(value, "<22>")
var result strings.Builder
result.Grow(len(value))
separatorPending := false
for _, r := range value {
if unicode.IsSpace(r) || unicode.IsControl(r) || unicode.In(r, unicode.Cf) {
if result.Len() > 0 {
separatorPending = true
}
continue
}
if separatorPending {
result.WriteByte(' ')
separatorPending = false
}
result.WriteRune(r)
}
return result.String()
}

View File

@@ -0,0 +1,138 @@
package llm
import (
"errors"
"fmt"
"reflect"
"strings"
"testing"
"unicode/utf8"
)
func TestProviderHTTPErrorEnvelopeParsing(t *testing.T) {
tests := []struct {
name string
body string
want providerErrorDetails
}{
{
name: "all supported string fields",
body: `{"error":{"message":"diagnostic","type":"invalid_request_error","code":"unsupported_parameter"}}`,
want: providerErrorDetails{providerMessage: "diagnostic", providerType: "invalid_request_error", providerCode: "unsupported_parameter"},
},
{
name: "integer code",
body: `{"error":{"code":17}}`,
want: providerErrorDetails{providerCode: "17"},
},
{
name: "fractional code",
body: `{"error":{"code":1.25}}`,
want: providerErrorDetails{providerCode: "1.25"},
},
{
name: "exponent code",
body: `{"error":{"code":6.02e+23}}`,
want: providerErrorDetails{providerCode: "6.02e+23"},
},
{
name: "invalid fields do not discard valid fields",
body: `{"error":{"message":null,"type":"invalid_request_error","code":false}}`,
want: providerErrorDetails{providerType: "invalid_request_error"},
},
{
name: "unknown fields are ignored",
body: `{"trace":"do not retain","error":{"param":"temperature","metadata":{"secret":"x"}}}`,
want: providerErrorDetails{},
},
{name: "missing error", body: `{}`, want: providerErrorDetails{}},
{name: "null error", body: `{"error":null}`, want: providerErrorDetails{}},
{name: "scalar error", body: `{"error":"nope"}`, want: providerErrorDetails{}},
{name: "empty error", body: `{"error":{}}`, want: providerErrorDetails{}},
{name: "malformed", body: `{"error":`, want: providerErrorDetails{}},
{name: "truncated", body: `{"error":{"message":"x"`, want: providerErrorDetails{}},
{name: "trailing garbage", body: `{"error":{"message":"x"}} garbage`, want: providerErrorDetails{}},
{name: "second document", body: `{"error":{"message":"x"}} {}`, want: providerErrorDetails{}},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
if got := parseProviderErrorEnvelope([]byte(tc.body)); !reflect.DeepEqual(got, tc.want) {
t.Fatalf("parseProviderErrorEnvelope() = %#v, want %#v", got, tc.want)
}
})
}
}
func TestProviderErrorTextNormalizationAndLimits(t *testing.T) {
validIdentifier := strings.Repeat("界", maxProviderErrorIdentifierRunes)
validMessage := strings.Repeat("界", maxProviderErrorMessageRunes)
tests := []struct {
name string
got string
want string
}{
{name: "multibyte text", got: "Grüße 世界", want: "Grüße 世界"},
{name: "invalid UTF-8", got: string([]byte{'a', 0xff, 'b'}), want: "a<>b"},
{name: "whitespace control and format runs", got: " \n\talpha\x00\u200b\u200bbeta \r ", want: "alpha beta"},
{name: "blank normalization", got: "\t\u200b\n", want: ""},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
if got := normalizeProviderErrorText(tc.got); got != tc.want {
t.Fatalf("normalizeProviderErrorText() = %q, want %q", got, tc.want)
}
})
}
if got := normalizeProviderErrorIdentifier(validIdentifier); got != validIdentifier {
t.Fatalf("exact identifier boundary = %q, want retained value", got)
}
if got := normalizeProviderErrorIdentifier(validIdentifier + "界"); got != "" {
t.Fatalf("overlong identifier = %q, want empty", got)
}
if got := normalizeProviderErrorMessage(validMessage); got != validMessage {
t.Fatalf("exact message boundary = %q, want retained value", got)
}
wantTruncatedMessage := strings.Repeat("界", maxProviderErrorMessageRunes-1) + "…"
if got := normalizeProviderErrorMessage(validMessage + "界"); got != wantTruncatedMessage {
t.Fatalf("overlong message length = %d, want %d", utf8.RuneCountInString(got), maxProviderErrorMessageRunes)
}
}
func TestProviderHTTPErrorIdentityAndFormatting(t *testing.T) {
const marker = "provider-secret-marker"
err := newProviderHTTPError(429, providerErrorDetails{
providerCode: marker + "-code",
providerType: marker + "-type",
providerMessage: marker + "-message",
})
if err.StatusCode() != 429 || err.ProviderCode() != marker+"-code" || err.ProviderType() != marker+"-type" || err.ProviderMessage() != marker+"-message" {
t.Fatalf("accessors returned unexpected values: %#v", err)
}
if !errors.Is(err, ErrUnexpectedStatus) {
t.Fatalf("errors.Is(%v, ErrUnexpectedStatus) = false", err)
}
for _, rendered := range []string{fmt.Sprintf("%v", err), fmt.Sprintf("%+v", err), fmt.Sprintf("%#v", err)} {
if rendered != "llm returned non-success status: status=429" {
t.Fatalf("formatted error = %q", rendered)
}
if strings.Contains(rendered, marker) {
t.Fatalf("formatted error exposed provider marker: %q", rendered)
}
}
var nilError *ProviderHTTPError
if nilError.StatusCode() != 0 || nilError.ProviderCode() != "" || nilError.ProviderType() != "" || nilError.ProviderMessage() != "" {
t.Fatal("nil accessors returned provider values")
}
if nilError.Error() != "llm returned non-success status" || nilError.GoString() != "llm returned non-success status" || !errors.Is(nilError, ErrUnexpectedStatus) {
t.Fatalf("nil error behavior is not safe: %v", nilError)
}
zero := &ProviderHTTPError{}
if zero.Error() != "llm returned non-success status" || zero.GoString() != "llm returned non-success status" || !errors.Is(zero, ErrUnexpectedStatus) {
t.Fatalf("zero error behavior is not safe: %v", zero)
}
}