open-source/cursor-byok
1
0
Fork 0
mirror of https://wget.la/https://github.com/leookun/cursor-byok synced 2026-08-17 03:27:02 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: gpt-5.6 support

Browse Source
This commit is contained in:
leokun
2026-07-10 11:38:45 +08:00
parent 6ab537ad4e
commit e0aa270328
15 changed files with 70 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/backend/agent/model/openai.go
+17 -9
View File
@@ -29,7 +29,7 @@ type openAIRequestBody struct {
Tools []json.RawMessage `json:"tools,omitempty"`
Messages []map[string]any `json:"messages"`
Stream bool `json:"stream"`
MaxTokens int `json:"max_tokens"`
MaxTokens int `json:"max_tokens,omitempty"`
StreamOptions map[string]any `json:"stream_options"`
ReasoningEffort string `json:"reasoning_effort,omitempty"`
PromptCacheKey string `json:"prompt_cache_key,omitempty"`
@@ -41,7 +41,7 @@ type openAIResponsesRequestBody struct {
Input []map[string]any `json:"input"`
Tools []map[string]any `json:"tools,omitempty"`
Stream bool `json:"stream"`
MaxOutputTokens int `json:"max_output_tokens"`
MaxOutputTokens int `json:"max_output_tokens,omitempty"`
Reasoning *openAIResponsesReasoning `json:"reasoning,omitempty"`
Include []string `json:"include,omitempty"`
PromptCacheKey string `json:"prompt_cache_key,omitempty"`
@@ -455,9 +455,11 @@ func (adapter *OpenAIAdapter) streamChatCompletions(ctx context.Context, req Str
Model: modelID,
Messages: normalizedMessages,
Stream: true,
MaxTokens: req.MaxTokens,
StreamOptions: map[string]any{"include_usage": true},
}
if shouldSendOpenAIMaxOutputTokens(modelID) {
requestBody.MaxTokens = req.MaxTokens
}
if key := openAIPromptCacheKey(req, modelID); key != "" {
requestBody.PromptCacheKey = key
}
@@ -914,12 +916,14 @@ func (adapter *OpenAIAdapter) streamResponses(ctx context.Context, req StreamReq
return err
}
requestBody := openAIResponsesRequestBody{
Model: modelID,
Instructions: instructions,
Input: input,
Stream: true,
MaxOutputTokens: req.MaxTokens,
Store: false,
Model: modelID,
Instructions: instructions,
Input: input,
Stream: true,
Store: false,
}
if shouldSendOpenAIMaxOutputTokens(modelID) {
requestBody.MaxOutputTokens = req.MaxTokens
}
if key := openAIPromptCacheKey(req, modelID); key != "" {
requestBody.PromptCacheKey = key
@@ -1844,6 +1848,10 @@ func normalizeOpenAIProviderMessages(messages []Message, thinkingEnabled bool) (
return items, nil
}
func shouldSendOpenAIMaxOutputTokens(modelID string) bool {
return !strings.Contains(strings.ToLower(strings.TrimSpace(modelID)), "gpt")
}
func shouldIncludeOpenAIReasoningContent(message Message, thinkingEnabled bool) bool {
if strings.TrimSpace(message.ReasoningContent) != "" {
return true
internal/backend/server/config/types.go
+2 -2
View File
@@ -152,7 +152,7 @@ func NormalizeModelAdapterConfigs(input []ModelAdapterConfig) ([]ModelAdapterCon
case next.ModelID == "":
return nil, errors.New("模型适配器 modelID 不能为空")
case next.Type == "openai" && next.ReasoningEffort == "":
return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh")
return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh、max")
case next.Type == "openai" && next.OpenAIEndpoint == "":
return nil, errors.New("模型适配器 openAIEndpoint 仅支持 /v1/responses、/v1/chat/completions 或 /custom（自定义路径）")
case next.Type == "openai" && next.OpenAIExtraParamsEnabled:
@@ -216,7 +216,7 @@ func normalizeReasoningEffort(value string) string {
switch strings.ToLower(strings.TrimSpace(value)) {
case "", "medium":
return "medium"
case "low", "high", "xhigh":
case "low", "high", "xhigh", "max":
return strings.ToLower(strings.TrimSpace(value))
default:
return ""
internal/backend/server/upstream/mocks.go
+2 -2
View File
@@ -746,7 +746,7 @@ func buildThinkingEffortVariantDisplayName(modelDisplayName string, effortValue
func thinkingEffortValuesForAdapter(adapterType string) []string {
values := []string{"disabled", "low", "medium", "high", "xhigh"}
if strings.EqualFold(strings.TrimSpace(adapterType), "anthropic") {
if adapterType := strings.ToLower(strings.TrimSpace(adapterType)); adapterType == "openai" || adapterType == "anthropic" {
values = append(values, "max")
}
return values
@@ -773,7 +773,7 @@ func defaultThinkingEffortForAdapter(adapter legacyruntime.ModelAdapterConfig) s
if strings.EqualFold(strings.TrimSpace(adapter.Type), "anthropic") {
return normalizeAvailableModelThinkingEffort(adapter.AnthropicThinkingEffort, true, "xhigh")
}
return normalizeAvailableModelThinkingEffort(adapter.ReasoningEffort, false, "medium")
return normalizeAvailableModelThinkingEffort(adapter.ReasoningEffort, true, "medium")
}
func normalizeAvailableModelThinkingEffort(raw string, allowMax bool, fallback string) string {
internal/client/model_adapter_benchmark.go
+1 -1
View File
@@ -668,7 +668,7 @@ func normalizeModelAdapterTestType(value string) string {
func normalizeModelAdapterTestReasoning(value string) string {
switch strings.ToLower(strings.TrimSpace(value)) {
case "low", "medium", "high", "xhigh":
case "low", "medium", "high", "xhigh", "max":
return strings.ToLower(strings.TrimSpace(value))
default:
return "medium"
internal/runtime/local_runtime.go
+2 -2
View File
@@ -138,7 +138,7 @@ func NormalizeModelAdapterConfigs(input []ModelAdapterConfig) ([]ModelAdapterCon
case next.ModelID == "":
return nil, errors.New("模型适配器 modelID 不能为空")
case next.Type == "openai" && next.ReasoningEffort == "":
return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh")
return nil, errors.New("模型适配器 reasoningEffort 仅支持 low、medium、high、xhigh、max")
case next.Type == "openai" && next.OpenAIEndpoint == "":
return nil, errors.New("模型适配器 openAIEndpoint 仅支持 /v1/responses 或 /v1/chat/completions")
case next.Type == "openai" && next.OpenAIExtraParamsEnabled:
@@ -202,7 +202,7 @@ func normalizeReasoningEffort(value string) string {
switch strings.ToLower(strings.TrimSpace(value)) {
case "", "medium":
return "medium"
case "low", "high", "xhigh":
case "low", "high", "xhigh", "max":
return strings.ToLower(strings.TrimSpace(value))
default:
return ""