feat: support claude-opus-4-7 (#4293)

* feat: support claude-opus-4-7

* feat: summarized display for opus 4.7
This commit is contained in:
papersnake
2026-04-17 13:52:34 +08:00
committed by GitHub
parent 22e509c1ef
commit 47d7bca268
9 changed files with 107 additions and 30 deletions
+6
View File
@@ -18,6 +18,7 @@ var awsModelIDMap = map[string]string{
"claude-haiku-4-5-20251001": "anthropic.claude-haiku-4-5-20251001-v1:0",
"claude-opus-4-5-20251101": "anthropic.claude-opus-4-5-20251101-v1:0",
"claude-opus-4-6": "anthropic.claude-opus-4-6-v1",
"claude-opus-4-7": "anthropic.claude-opus-4-7",
// Nova models
"nova-micro-v1:0": "amazon.nova-micro-v1:0",
"nova-lite-v1:0": "amazon.nova-lite-v1:0",
@@ -91,6 +92,11 @@ var awsModelCanCrossRegionMap = map[string]map[string]bool{
"ap": true,
"eu": true,
},
"anthropic.claude-opus-4-7": {
"us": true,
"ap": true,
"eu": true,
},
"anthropic.claude-haiku-4-5-20251001-v1:0": {
"us": true,
"ap": true,
+7
View File
@@ -26,6 +26,13 @@ var ModelList = []string{
"claude-opus-4-6-medium",
"claude-opus-4-6-low",
"claude-sonnet-4-6",
"claude-opus-4-7",
"claude-opus-4-7-max",
"claude-opus-4-7-xhigh",
"claude-opus-4-7-high",
"claude-opus-4-7-medium",
"claude-opus-4-7-low",
"claude-opus-4-7-thinking",
}
var ChannelName = "claude"
+35 -16
View File
@@ -154,33 +154,52 @@ func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRe
}
if baseModel, effortLevel, ok := reasoning.TrimEffortSuffix(textRequest.Model); ok && effortLevel != "" &&
strings.HasPrefix(textRequest.Model, "claude-opus-4-6") {
(strings.HasPrefix(textRequest.Model, "claude-opus-4-6") || strings.HasPrefix(textRequest.Model, "claude-opus-4-7")) {
claudeRequest.Model = baseModel
claudeRequest.Thinking = &dto.Thinking{
Type: "adaptive",
}
claudeRequest.OutputConfig = json.RawMessage(fmt.Sprintf(`{"effort":"%s"}`, effortLevel))
claudeRequest.TopP = nil
claudeRequest.Temperature = common.GetPointer[float64](1.0)
if strings.HasPrefix(baseModel, "claude-opus-4-7") {
// Opus 4.7 rejects non-default temperature/top_p/top_k with 400
// and defaults display to "omitted"; restore the 4.6 visible summary.
claudeRequest.Thinking.Display = "summarized"
claudeRequest.Temperature = nil
claudeRequest.TopP = nil
claudeRequest.TopK = nil
} else {
claudeRequest.TopP = nil
claudeRequest.Temperature = common.GetPointer[float64](1.0)
}
} else if model_setting.GetClaudeSettings().ThinkingAdapterEnabled &&
strings.HasSuffix(textRequest.Model, "-thinking") {
// 因为BudgetTokens 必须大于1024
if claudeRequest.MaxTokens == nil || *claudeRequest.MaxTokens < 1280 {
claudeRequest.MaxTokens = common.GetPointer[uint](1280)
}
trimmedModel := strings.TrimSuffix(textRequest.Model, "-thinking")
if strings.HasPrefix(trimmedModel, "claude-opus-4-7") {
// Opus 4.7 rejects thinking.type="enabled"; use adaptive at high effort.
claudeRequest.Thinking = &dto.Thinking{Type: "adaptive", Display: "summarized"}
claudeRequest.OutputConfig = json.RawMessage(`{"effort":"high"}`)
claudeRequest.Temperature = nil
claudeRequest.TopP = nil
claudeRequest.TopK = nil
} else {
// 因为BudgetTokens 必须大于1024
if claudeRequest.MaxTokens == nil || *claudeRequest.MaxTokens < 1280 {
claudeRequest.MaxTokens = common.GetPointer[uint](1280)
}
// BudgetTokens 为 max_tokens 的 80%
claudeRequest.Thinking = &dto.Thinking{
Type: "enabled",
BudgetTokens: common.GetPointer[int](int(float64(*claudeRequest.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
// BudgetTokens 为 max_tokens 的 80%
claudeRequest.Thinking = &dto.Thinking{
Type: "enabled",
BudgetTokens: common.GetPointer[int](int(float64(*claudeRequest.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
}
// TODO: 临时处理
// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
claudeRequest.TopP = nil
claudeRequest.Temperature = common.GetPointer[float64](1.0)
}
// TODO: 临时处理
// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
claudeRequest.TopP = nil
claudeRequest.Temperature = common.GetPointer[float64](1.0)
if !model_setting.ShouldPreserveThinkingSuffix(textRequest.Model) {
claudeRequest.Model = strings.TrimSuffix(textRequest.Model, "-thinking")
claudeRequest.Model = trimmedModel
}
}
+1
View File
@@ -44,6 +44,7 @@ var claudeModelMap = map[string]string{
"claude-haiku-4-5-20251001": "claude-haiku-4-5@20251001",
"claude-opus-4-5-20251101": "claude-opus-4-5@20251101",
"claude-opus-4-6": "claude-opus-4-6",
"claude-opus-4-7": "claude-opus-4-7",
}
const anthropicVersion = "vertex-2023-10-16"
+32 -13
View File
@@ -53,30 +53,49 @@ func ClaudeHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *typ
}
if baseModel, effortLevel, ok := reasoning.TrimEffortSuffix(request.Model); ok && effortLevel != "" &&
strings.HasPrefix(request.Model, "claude-opus-4-6") {
(strings.HasPrefix(request.Model, "claude-opus-4-6") || strings.HasPrefix(request.Model, "claude-opus-4-7")) {
request.Model = baseModel
request.Thinking = &dto.Thinking{
Type: "adaptive",
}
request.OutputConfig = json.RawMessage(fmt.Sprintf(`{"effort":"%s"}`, effortLevel))
request.Temperature = common.GetPointer[float64](1.0)
if strings.HasPrefix(request.Model, "claude-opus-4-7") {
// Opus 4.7 rejects non-default temperature/top_p/top_k with 400
// and defaults display to "omitted"; restore the 4.6 visible summary.
request.Thinking.Display = "summarized"
request.Temperature = nil
request.TopP = nil
request.TopK = nil
} else {
request.Temperature = common.GetPointer[float64](1.0)
}
info.UpstreamModelName = request.Model
} else if model_setting.GetClaudeSettings().ThinkingAdapterEnabled &&
strings.HasSuffix(request.Model, "-thinking") {
if request.Thinking == nil {
// 因为BudgetTokens 必须大于1024
if request.MaxTokens == nil || *request.MaxTokens < 1280 {
request.MaxTokens = common.GetPointer[uint](1280)
}
baseModel := strings.TrimSuffix(request.Model, "-thinking")
if strings.HasPrefix(baseModel, "claude-opus-4-7") {
// Opus 4.7 rejects thinking.type="enabled"; use adaptive at high effort.
request.Thinking = &dto.Thinking{Type: "adaptive", Display: "summarized"}
request.OutputConfig = json.RawMessage(`{"effort":"high"}`)
request.Temperature = nil
request.TopP = nil
request.TopK = nil
} else {
// 因为BudgetTokens 必须大于1024
if request.MaxTokens == nil || *request.MaxTokens < 1280 {
request.MaxTokens = common.GetPointer[uint](1280)
}
// BudgetTokens 为 max_tokens 的 80%
request.Thinking = &dto.Thinking{
Type: "enabled",
BudgetTokens: common.GetPointer[int](int(float64(*request.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
// BudgetTokens 为 max_tokens 的 80%
request.Thinking = &dto.Thinking{
Type: "enabled",
BudgetTokens: common.GetPointer[int](int(float64(*request.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
}
// TODO: 临时处理
// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
request.Temperature = common.GetPointer[float64](1.0)
}
// TODO: 临时处理
// https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations-when-using-extended-thinking
request.Temperature = common.GetPointer[float64](1.0)
}
if !model_setting.ShouldPreserveThinkingSuffix(info.OriginModelName) {
request.Model = strings.TrimSuffix(request.Model, "-thinking")