Files
new-api/relaykit/relayconvert/internal/oai_chat/to_oai_responses_req.go
T
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

403 lines
9.9 KiB
Go

package oaichat
import (
"encoding/json"
"errors"
"fmt"
"strings"
"github.com/QuantumNous/new-api/relaykit/dto"
kitutil "github.com/QuantumNous/new-api/relaykit/relayconvert/kitutil"
"github.com/samber/lo"
)
func normalizeChatImageURLToString(v any) any {
switch vv := v.(type) {
case string:
return vv
case map[string]any:
if url := kitutil.Interface2String(vv["url"]); url != "" {
return url
}
return v
case dto.MessageImageUrl:
if vv.Url != "" {
return vv.Url
}
return v
case *dto.MessageImageUrl:
if vv != nil && vv.Url != "" {
return vv.Url
}
return v
default:
return v
}
}
func convertChatResponseFormatToResponsesText(reqFormat *dto.ResponseFormat) json.RawMessage {
if reqFormat == nil || strings.TrimSpace(reqFormat.Type) == "" {
return nil
}
format := map[string]any{
"type": reqFormat.Type,
}
if reqFormat.Type == "json_schema" && len(reqFormat.JsonSchema) > 0 {
var chatSchema map[string]any
if err := kitutil.Unmarshal(reqFormat.JsonSchema, &chatSchema); err == nil {
for key, value := range chatSchema {
if key == "type" {
continue
}
format[key] = value
}
if nested, ok := format["json_schema"].(map[string]any); ok {
for key, value := range nested {
if _, exists := format[key]; !exists {
format[key] = value
}
}
delete(format, "json_schema")
}
} else {
format["json_schema"] = reqFormat.JsonSchema
}
}
textRaw, _ := kitutil.Marshal(map[string]any{
"format": format,
})
return textRaw
}
func ChatCompletionsRequestToResponsesRequest(req *dto.GeneralOpenAIRequest) (*dto.OpenAIResponsesRequest, error) {
if req == nil {
return nil, errors.New("request is nil")
}
if req.Model == "" {
return nil, errors.New("model is required")
}
if lo.FromPtrOr(req.N, 1) > 1 {
return nil, fmt.Errorf("n>1 is not supported in responses compatibility mode")
}
var instructionsParts []string
inputItems := make([]map[string]any, 0, len(req.Messages))
for _, msg := range req.Messages {
role := strings.TrimSpace(msg.Role)
if role == "" {
continue
}
if role == "tool" || role == "function" {
callID := strings.TrimSpace(msg.ToolCallId)
var output any
if msg.Content == nil {
output = ""
} else if msg.IsStringContent() {
output = msg.StringContent()
} else {
if b, err := kitutil.Marshal(msg.Content); err == nil {
output = string(b)
} else {
output = fmt.Sprintf("%v", msg.Content)
}
}
if callID == "" {
inputItems = append(inputItems, map[string]any{
"role": "user",
"content": fmt.Sprintf("[tool_output_missing_call_id] %v", output),
})
continue
}
inputItems = append(inputItems, map[string]any{
"type": "function_call_output",
"call_id": callID,
"output": output,
})
continue
}
// Prefer mapping system/developer messages into `instructions`.
if role == "system" || role == "developer" {
if msg.Content == nil {
continue
}
if msg.IsStringContent() {
if s := strings.TrimSpace(msg.StringContent()); s != "" {
instructionsParts = append(instructionsParts, s)
}
continue
}
parts := msg.ParseContent()
var sb strings.Builder
for _, part := range parts {
if part.Type == dto.ContentTypeText && strings.TrimSpace(part.Text) != "" {
if sb.Len() > 0 {
sb.WriteString("\n")
}
sb.WriteString(part.Text)
}
}
if s := strings.TrimSpace(sb.String()); s != "" {
instructionsParts = append(instructionsParts, s)
}
continue
}
item := map[string]any{
"role": role,
}
if msg.Content == nil {
item["content"] = ""
inputItems = append(inputItems, item)
if role == "assistant" {
for _, tc := range msg.ParseToolCalls() {
if strings.TrimSpace(tc.ID) == "" {
continue
}
if tc.Type != "" && tc.Type != "function" {
continue
}
name := strings.TrimSpace(tc.Function.Name)
if name == "" {
continue
}
inputItems = append(inputItems, map[string]any{
"type": "function_call",
"call_id": tc.ID,
"name": name,
"arguments": tc.Function.Arguments,
})
}
}
continue
}
if msg.IsStringContent() {
item["content"] = msg.StringContent()
inputItems = append(inputItems, item)
if role == "assistant" {
for _, tc := range msg.ParseToolCalls() {
if strings.TrimSpace(tc.ID) == "" {
continue
}
if tc.Type != "" && tc.Type != "function" {
continue
}
name := strings.TrimSpace(tc.Function.Name)
if name == "" {
continue
}
inputItems = append(inputItems, map[string]any{
"type": "function_call",
"call_id": tc.ID,
"name": name,
"arguments": tc.Function.Arguments,
})
}
}
continue
}
parts := msg.ParseContent()
contentParts := make([]map[string]any, 0, len(parts))
for _, part := range parts {
switch part.Type {
case dto.ContentTypeText:
textType := "input_text"
if role == "assistant" {
textType = "output_text"
}
contentParts = append(contentParts, map[string]any{
"type": textType,
"text": part.Text,
})
case dto.ContentTypeImageURL:
contentParts = append(contentParts, map[string]any{
"type": "input_image",
"image_url": normalizeChatImageURLToString(part.ImageUrl),
})
case dto.ContentTypeInputAudio:
contentParts = append(contentParts, map[string]any{
"type": "input_audio",
"input_audio": part.InputAudio,
})
case dto.ContentTypeFile:
contentParts = append(contentParts, map[string]any{
"type": "input_file",
"file": part.File,
})
case dto.ContentTypeVideoUrl:
contentParts = append(contentParts, map[string]any{
"type": "input_video",
"video_url": part.VideoUrl,
})
default:
contentParts = append(contentParts, map[string]any{
"type": part.Type,
})
}
}
item["content"] = contentParts
inputItems = append(inputItems, item)
if role == "assistant" {
for _, tc := range msg.ParseToolCalls() {
if strings.TrimSpace(tc.ID) == "" {
continue
}
if tc.Type != "" && tc.Type != "function" {
continue
}
name := strings.TrimSpace(tc.Function.Name)
if name == "" {
continue
}
inputItems = append(inputItems, map[string]any{
"type": "function_call",
"call_id": tc.ID,
"name": name,
"arguments": tc.Function.Arguments,
})
}
}
}
inputRaw, err := kitutil.Marshal(inputItems)
if err != nil {
return nil, err
}
var instructionsRaw json.RawMessage
if len(instructionsParts) > 0 {
instructions := strings.Join(instructionsParts, "\n\n")
instructionsRaw, _ = kitutil.Marshal(instructions)
}
var toolsRaw json.RawMessage
if req.Tools != nil {
tools := make([]map[string]any, 0, len(req.Tools))
for _, tool := range req.Tools {
switch tool.Type {
case "function":
tools = append(tools, map[string]any{
"type": "function",
"name": tool.Function.Name,
"description": tool.Function.Description,
"parameters": tool.Function.Parameters,
})
default:
// Best-effort: keep original tool shape for unknown types.
var m map[string]any
if b, err := kitutil.Marshal(tool); err == nil {
_ = kitutil.Unmarshal(b, &m)
}
if len(m) == 0 {
m = map[string]any{"type": tool.Type}
}
tools = append(tools, m)
}
}
toolsRaw, _ = kitutil.Marshal(tools)
}
var toolChoiceRaw json.RawMessage
if req.ToolChoice != nil {
switch v := req.ToolChoice.(type) {
case string:
toolChoiceRaw, _ = kitutil.Marshal(v)
default:
var m map[string]any
if b, err := kitutil.Marshal(v); err == nil {
_ = kitutil.Unmarshal(b, &m)
}
if m == nil {
toolChoiceRaw, _ = kitutil.Marshal(v)
} else if t, _ := m["type"].(string); t == "function" {
// Chat: {"type":"function","function":{"name":"..."}}
// Responses: {"type":"function","name":"..."}
if name, ok := m["name"].(string); ok && name != "" {
toolChoiceRaw, _ = kitutil.Marshal(map[string]any{
"type": "function",
"name": name,
})
} else if fn, ok := m["function"].(map[string]any); ok {
if name, ok := fn["name"].(string); ok && name != "" {
toolChoiceRaw, _ = kitutil.Marshal(map[string]any{
"type": "function",
"name": name,
})
} else {
toolChoiceRaw, _ = kitutil.Marshal(v)
}
} else {
toolChoiceRaw, _ = kitutil.Marshal(v)
}
} else {
toolChoiceRaw, _ = kitutil.Marshal(v)
}
}
}
var parallelToolCallsRaw json.RawMessage
if req.ParallelTooCalls != nil {
parallelToolCallsRaw, _ = kitutil.Marshal(*req.ParallelTooCalls)
}
textRaw := convertChatResponseFormatToResponsesText(req.ResponseFormat)
maxOutputTokens := lo.FromPtrOr(req.MaxTokens, uint(0))
maxCompletionTokens := lo.FromPtrOr(req.MaxCompletionTokens, uint(0))
if maxCompletionTokens > maxOutputTokens {
maxOutputTokens = maxCompletionTokens
}
// OpenAI Responses API rejects max_output_tokens < 16 when explicitly provided.
//if maxOutputTokens > 0 && maxOutputTokens < 16 {
// maxOutputTokens = 16
//}
var topP *float64
if req.TopP != nil {
topP = kitutil.GetPointer(lo.FromPtr(req.TopP))
}
out := &dto.OpenAIResponsesRequest{
Model: req.Model,
Input: inputRaw,
Instructions: instructionsRaw,
Stream: req.Stream,
Temperature: req.Temperature,
Text: textRaw,
ToolChoice: toolChoiceRaw,
Tools: toolsRaw,
TopP: topP,
User: req.User,
ParallelToolCalls: parallelToolCallsRaw,
Store: req.Store,
Metadata: req.Metadata,
}
if req.MaxTokens != nil || req.MaxCompletionTokens != nil {
out.MaxOutputTokens = lo.ToPtr(maxOutputTokens)
}
if req.ReasoningEffort != "" {
out.Reasoning = &dto.Reasoning{
Effort: req.ReasoningEffort,
Summary: "detailed",
}
}
return out, nil
}