* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
209 lines
4.9 KiB
Go
209 lines
4.9 KiB
Go
package operation_setting
|
||
|
||
import (
|
||
"fmt"
|
||
"sort"
|
||
"strconv"
|
||
"strings"
|
||
|
||
"github.com/QuantumNous/new-api/relaykit/types"
|
||
)
|
||
|
||
type StatusCodeRange struct {
|
||
Start int
|
||
End int
|
||
}
|
||
|
||
var AutomaticDisableStatusCodeRanges = []StatusCodeRange{{Start: 401, End: 401}}
|
||
|
||
// Default behavior matches legacy hardcoded retry rules in controller/relay.go shouldRetry:
|
||
// retry for 1xx, 3xx, 4xx(except 400/408), 5xx(except 504/524), and no retry for 2xx.
|
||
var AutomaticRetryStatusCodeRanges = []StatusCodeRange{
|
||
{Start: 100, End: 199},
|
||
{Start: 300, End: 399},
|
||
{Start: 401, End: 407},
|
||
{Start: 409, End: 499},
|
||
{Start: 500, End: 503},
|
||
{Start: 505, End: 523},
|
||
{Start: 525, End: 599},
|
||
}
|
||
|
||
var alwaysSkipRetryStatusCodes = map[int]struct{}{
|
||
504: {},
|
||
524: {},
|
||
}
|
||
|
||
var alwaysSkipRetryCodes = map[types.ErrorCode]struct{}{
|
||
types.ErrorCodeBadResponseBody: {},
|
||
}
|
||
|
||
func AutomaticDisableStatusCodesToString() string {
|
||
return statusCodeRangesToString(AutomaticDisableStatusCodeRanges)
|
||
}
|
||
|
||
func AutomaticDisableStatusCodesFromString(s string) error {
|
||
ranges, err := ParseHTTPStatusCodeRanges(s)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
AutomaticDisableStatusCodeRanges = ranges
|
||
return nil
|
||
}
|
||
|
||
func ShouldDisableByStatusCode(code int) bool {
|
||
return shouldMatchStatusCodeRanges(AutomaticDisableStatusCodeRanges, code)
|
||
}
|
||
|
||
func AutomaticRetryStatusCodesToString() string {
|
||
return statusCodeRangesToString(AutomaticRetryStatusCodeRanges)
|
||
}
|
||
|
||
func AutomaticRetryStatusCodesFromString(s string) error {
|
||
ranges, err := ParseHTTPStatusCodeRanges(s)
|
||
if err != nil {
|
||
return err
|
||
}
|
||
AutomaticRetryStatusCodeRanges = ranges
|
||
return nil
|
||
}
|
||
|
||
func IsAlwaysSkipRetryStatusCode(code int) bool {
|
||
_, exists := alwaysSkipRetryStatusCodes[code]
|
||
return exists
|
||
}
|
||
|
||
func IsAlwaysSkipRetryCode(errorCode types.ErrorCode) bool {
|
||
_, exists := alwaysSkipRetryCodes[errorCode]
|
||
return exists
|
||
}
|
||
|
||
func ShouldRetryByStatusCode(code int) bool {
|
||
if IsAlwaysSkipRetryStatusCode(code) {
|
||
return false
|
||
}
|
||
return shouldMatchStatusCodeRanges(AutomaticRetryStatusCodeRanges, code)
|
||
}
|
||
|
||
func statusCodeRangesToString(ranges []StatusCodeRange) string {
|
||
if len(ranges) == 0 {
|
||
return ""
|
||
}
|
||
parts := make([]string, 0, len(ranges))
|
||
for _, r := range ranges {
|
||
if r.Start == r.End {
|
||
parts = append(parts, strconv.Itoa(r.Start))
|
||
continue
|
||
}
|
||
parts = append(parts, fmt.Sprintf("%d-%d", r.Start, r.End))
|
||
}
|
||
return strings.Join(parts, ",")
|
||
}
|
||
|
||
func shouldMatchStatusCodeRanges(ranges []StatusCodeRange, code int) bool {
|
||
if code < 100 || code > 599 {
|
||
return false
|
||
}
|
||
for _, r := range ranges {
|
||
if code < r.Start {
|
||
return false
|
||
}
|
||
if code <= r.End {
|
||
return true
|
||
}
|
||
}
|
||
return false
|
||
}
|
||
|
||
func ParseHTTPStatusCodeRanges(input string) ([]StatusCodeRange, error) {
|
||
input = strings.TrimSpace(input)
|
||
if input == "" {
|
||
return nil, nil
|
||
}
|
||
|
||
input = strings.NewReplacer(",", ",").Replace(input)
|
||
segments := strings.Split(input, ",")
|
||
|
||
var ranges []StatusCodeRange
|
||
var invalid []string
|
||
|
||
for _, seg := range segments {
|
||
seg = strings.TrimSpace(seg)
|
||
if seg == "" {
|
||
continue
|
||
}
|
||
r, err := parseHTTPStatusCodeToken(seg)
|
||
if err != nil {
|
||
invalid = append(invalid, seg)
|
||
continue
|
||
}
|
||
ranges = append(ranges, r)
|
||
}
|
||
|
||
if len(invalid) > 0 {
|
||
return nil, fmt.Errorf("invalid http status code rules: %s", strings.Join(invalid, ", "))
|
||
}
|
||
if len(ranges) == 0 {
|
||
return nil, nil
|
||
}
|
||
|
||
sort.Slice(ranges, func(i, j int) bool {
|
||
if ranges[i].Start == ranges[j].Start {
|
||
return ranges[i].End < ranges[j].End
|
||
}
|
||
return ranges[i].Start < ranges[j].Start
|
||
})
|
||
|
||
merged := []StatusCodeRange{ranges[0]}
|
||
for _, r := range ranges[1:] {
|
||
last := &merged[len(merged)-1]
|
||
if r.Start <= last.End+1 {
|
||
if r.End > last.End {
|
||
last.End = r.End
|
||
}
|
||
continue
|
||
}
|
||
merged = append(merged, r)
|
||
}
|
||
|
||
return merged, nil
|
||
}
|
||
|
||
func parseHTTPStatusCodeToken(token string) (StatusCodeRange, error) {
|
||
token = strings.TrimSpace(token)
|
||
token = strings.ReplaceAll(token, " ", "")
|
||
if token == "" {
|
||
return StatusCodeRange{}, fmt.Errorf("empty token")
|
||
}
|
||
|
||
if strings.Contains(token, "-") {
|
||
parts := strings.Split(token, "-")
|
||
if len(parts) != 2 || parts[0] == "" || parts[1] == "" {
|
||
return StatusCodeRange{}, fmt.Errorf("invalid range token: %s", token)
|
||
}
|
||
start, err := strconv.Atoi(parts[0])
|
||
if err != nil {
|
||
return StatusCodeRange{}, fmt.Errorf("invalid range start: %s", token)
|
||
}
|
||
end, err := strconv.Atoi(parts[1])
|
||
if err != nil {
|
||
return StatusCodeRange{}, fmt.Errorf("invalid range end: %s", token)
|
||
}
|
||
if start > end {
|
||
return StatusCodeRange{}, fmt.Errorf("range start > end: %s", token)
|
||
}
|
||
if start < 100 || end > 599 {
|
||
return StatusCodeRange{}, fmt.Errorf("range out of bounds: %s", token)
|
||
}
|
||
return StatusCodeRange{Start: start, End: end}, nil
|
||
}
|
||
|
||
code, err := strconv.Atoi(token)
|
||
if err != nil {
|
||
return StatusCodeRange{}, fmt.Errorf("invalid status code: %s", token)
|
||
}
|
||
if code < 100 || code > 599 {
|
||
return StatusCodeRange{}, fmt.Errorf("status code out of bounds: %s", token)
|
||
}
|
||
return StatusCodeRange{Start: code, End: code}, nil
|
||
}
|