Files
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

112 lines
3.5 KiB
Go

package model_setting
import (
"fmt"
"net/http"
"strings"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/setting/config"
)
//var claudeHeadersSettings = map[string][]string{}
//
//var ClaudeThinkingAdapterEnabled = true
//var ClaudeThinkingAdapterMaxTokens = 8192
//var ClaudeThinkingAdapterBudgetTokensPercentage = 0.8
// ClaudeSettings 定义Claude模型的配置
type ClaudeSettings struct {
HeadersSettings map[string]map[string][]string `json:"model_headers_settings"`
DefaultMaxTokens map[string]int `json:"default_max_tokens"`
ThinkingAdapterEnabled bool `json:"thinking_adapter_enabled"`
ThinkingAdapterBudgetTokensPercentage float64 `json:"thinking_adapter_budget_tokens_percentage"`
}
// 默认配置
var defaultClaudeSettings = ClaudeSettings{
HeadersSettings: map[string]map[string][]string{},
ThinkingAdapterEnabled: true,
DefaultMaxTokens: map[string]int{
"default": 8192,
},
ThinkingAdapterBudgetTokensPercentage: 0.8,
}
// 全局实例
var claudeSettings = defaultClaudeSettings
func init() {
// 注册到全局配置管理器
config.GlobalConfig.Register("claude", &claudeSettings)
}
// GetClaudeSettings 获取Claude配置
func GetClaudeSettings() *ClaudeSettings {
// check default max tokens must have default key
if _, ok := claudeSettings.DefaultMaxTokens["default"]; !ok {
claudeSettings.DefaultMaxTokens["default"] = 8192
}
return &claudeSettings
}
func (c *ClaudeSettings) WriteHeaders(originModel string, httpHeader *http.Header) {
if headers, ok := c.HeadersSettings[originModel]; ok {
for headerKey, headerValues := range headers {
mergedValues := normalizeHeaderListValues(
append(append([]string(nil), httpHeader.Values(headerKey)...), headerValues...),
)
if len(mergedValues) == 0 {
continue
}
httpHeader.Set(headerKey, strings.Join(mergedValues, ","))
}
}
}
func normalizeHeaderListValues(values []string) []string {
normalizedValues := make([]string, 0, len(values))
seenValues := make(map[string]struct{}, len(values))
for _, value := range values {
for _, item := range strings.Split(value, ",") {
normalizedItem := strings.TrimSpace(item)
if normalizedItem == "" {
continue
}
if _, exists := seenValues[normalizedItem]; exists {
continue
}
seenValues[normalizedItem] = struct{}{}
normalizedValues = append(normalizedValues, normalizedItem)
}
}
return normalizedValues
}
func (c *ClaudeSettings) GetDefaultMaxTokens(model string) int {
if maxTokens, ok := c.DefaultMaxTokens[model]; ok {
return maxTokens
}
return c.DefaultMaxTokens["default"]
}
// ValidateClaudeDefaultMaxTokens validates the JSON persisted by the option
// API. Zero stays allowed — the current Messages API accepts max_tokens: 0 as
// cache pre-warming — but negative values are rejected because they would
// wrap into huge unsigned values during request conversion.
func ValidateClaudeDefaultMaxTokens(value string) error {
var settings map[string]int
if err := common.UnmarshalJsonStr(value, &settings); err != nil {
return fmt.Errorf("Claude default max tokens must be a JSON map of model to integer: %w", err)
}
if settings == nil {
return fmt.Errorf("Claude default max tokens must be a JSON map of model to integer")
}
for model, maxTokens := range settings {
if maxTokens < 0 {
return fmt.Errorf("negative Claude default max_tokens %d for %q", maxTokens, model)
}
}
return nil
}