lywsvip/CLIProxyAPIPlus
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPIPlus.git synced 2026-05-10 05:16:16 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'router-for-me:main' into main

Browse Source
This commit is contained in:
Luis Pater
2026-01-01 21:03:16 +08:00
committed by GitHub
parent 19232c6388 750b930679
commit ba486ca6b7
18 changed files with 1233 additions and 138 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
internal/runtime/executor/antigravity_executor.go
View File

@@ -96,9 +96,9 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
to := sdktranslator.FromString("antigravity")
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
@@ -191,9 +191,9 @@ func (e *AntigravityExecutor) executeClaudeNonStream(ctx context.Context, auth *
to := sdktranslator.FromString("antigravity")
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
translated = normalizeAntigravityThinking(req.Model, translated, true)
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
@@ -527,9 +527,9 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
to := sdktranslator.FromString("antigravity")
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
translated = applyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = ApplyThinkingMetadataCLI(translated, req.Metadata, req.Model)
translated = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
translated = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, translated)
translated = normalizeAntigravityThinking(req.Model, translated, isClaude)
translated = applyPayloadConfigWithRoot(e.cfg, req.Model, "antigravity", "request", translated)
@@ -697,8 +697,8 @@ func (e *AntigravityExecutor) CountTokens(ctx context.Context, auth *cliproxyaut
for idx, baseURL := range baseURLs {
payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
payload = applyThinkingMetadataCLI(payload, req.Metadata, req.Model)
payload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, payload)
payload = ApplyThinkingMetadataCLI(payload, req.Metadata, req.Model)
payload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, payload)
payload = normalizeAntigravityThinking(req.Model, payload, isClaude)
payload = deleteJSONField(payload, "project")
payload = deleteJSONField(payload, "model")

10
internal/runtime/executor/gemini_cli_executor.go
View File

@@ -78,9 +78,9 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
basePayload = applyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
basePayload = ApplyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
basePayload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, basePayload)
basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, basePayload)
basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -217,9 +217,9 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
from := opts.SourceFormat
to := sdktranslator.FromString("gemini-cli")
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
basePayload = applyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
basePayload = ApplyThinkingMetadataCLI(basePayload, req.Metadata, req.Model)
basePayload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, basePayload)
basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
basePayload = util.ApplyDefaultThinkingIfNeededCLI(req.Model, req.Metadata, basePayload)
basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -421,7 +421,7 @@ func (e *GeminiCLIExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.
// Gemini CLI endpoint when iterating fallback variants.
for _, attemptModel := range models {
payload := sdktranslator.TranslateRequest(from, to, attemptModel, bytes.Clone(req.Payload), false)
payload = applyThinkingMetadataCLI(payload, req.Metadata, req.Model)
payload = ApplyThinkingMetadataCLI(payload, req.Metadata, req.Model)
payload = util.ApplyGemini3ThinkingLevelFromMetadataCLI(req.Model, req.Metadata, payload)
payload = deleteJSONField(payload, "project")
payload = deleteJSONField(payload, "model")

71
internal/runtime/executor/iflow_executor.go
View File

@@ -441,21 +441,18 @@ func ensureToolsArray(body []byte) []byte {
return updated
}
// preserveReasoningContentInMessages ensures reasoning_content from assistant messages in the
// conversation history is preserved when sending to iFlow models that support thinking.
// This is critical for multi-turn conversations where the model needs to see its previous
// reasoning to maintain coherent thought chains across tool calls and conversation turns.
// preserveReasoningContentInMessages checks if reasoning_content from assistant messages
// is preserved in conversation history for iFlow models that support thinking.
// This is helpful for multi-turn conversations where the model may benefit from seeing
// its previous reasoning to maintain coherent thought chains.
//
// For GLM-4.7 and MiniMax-M2.1, the full assistant response (including reasoning) must be
// appended back into message history before the next call.
// For GLM-4.6/4.7 and MiniMax M2/M2.1, it is recommended to include the full assistant
// response (including reasoning_content) in message history for better context continuity.
func preserveReasoningContentInMessages(body []byte) []byte {
model := strings.ToLower(gjson.GetBytes(body, "model").String())
// Only apply to models that support thinking with history preservation
needsPreservation := strings.HasPrefix(model, "glm-4.7") ||
strings.HasPrefix(model, "glm-4-7") ||
strings.HasPrefix(model, "minimax-m2.1") ||
strings.HasPrefix(model, "minimax-m2-1")
needsPreservation := strings.HasPrefix(model, "glm-4") || strings.HasPrefix(model, "minimax-m2")
if !needsPreservation {
return body
@@ -493,45 +490,35 @@ func preserveReasoningContentInMessages(body []byte) []byte {
// This should be called after NormalizeThinkingConfig has processed the payload.
//
// Model-specific handling:
// - GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false}
// - MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
// - Other iFlow models: Uses chat_template_kwargs.enable_thinking (boolean)
// - GLM-4.6/4.7: Uses chat_template_kwargs.enable_thinking (boolean) and chat_template_kwargs.clear_thinking=false
// - MiniMax M2/M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
func applyIFlowThinkingConfig(body []byte) []byte {
effort := gjson.GetBytes(body, "reasoning_effort")
model := strings.ToLower(gjson.GetBytes(body, "model").String())
// Check if thinking should be enabled
val := ""
if effort.Exists() {
val = strings.ToLower(strings.TrimSpace(effort.String()))
if !effort.Exists() {
return body
}
enableThinking := effort.Exists() && val != "none" && val != ""
model := strings.ToLower(gjson.GetBytes(body, "model").String())
val := strings.ToLower(strings.TrimSpace(effort.String()))
enableThinking := val != "none" && val != ""
// Remove reasoning_effort as we'll convert to model-specific format
if effort.Exists() {
body, _ = sjson.DeleteBytes(body, "reasoning_effort")
}
body, _ = sjson.DeleteBytes(body, "reasoning_effort")
body, _ = sjson.DeleteBytes(body, "thinking")
// GLM-4.7: Use extra_body with thinking config and clear_thinking: false
if strings.HasPrefix(model, "glm-4.7") || strings.HasPrefix(model, "glm-4-7") {
if enableThinking {
body, _ = sjson.SetBytes(body, "extra_body.thinking.type", "enabled")
body, _ = sjson.SetBytes(body, "extra_body.clear_thinking", false)
}
return body
}
// MiniMax-M2.1: Use reasoning_split=true for interleaved thinking
if strings.HasPrefix(model, "minimax-m2.1") || strings.HasPrefix(model, "minimax-m2-1") {
if enableThinking {
body, _ = sjson.SetBytes(body, "reasoning_split", true)
}
return body
}
// Other iFlow models (including GLM-4.6): Use chat_template_kwargs.enable_thinking
if effort.Exists() {
// GLM-4.6/4.7: Use chat_template_kwargs
if strings.HasPrefix(model, "glm-4") {
body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
if enableThinking {
body, _ = sjson.SetBytes(body, "chat_template_kwargs.clear_thinking", false)
}
return body
}
// MiniMax M2/M2.1: Use reasoning_split
if strings.HasPrefix(model, "minimax-m2") {
body, _ = sjson.SetBytes(body, "reasoning_split", enableThinking)
return body
}
return body

38
internal/runtime/executor/payload_helpers.go
View File

@@ -14,32 +14,54 @@ import (
// ApplyThinkingMetadata applies thinking config from model suffix metadata (e.g., (high), (8192))
// for standard Gemini format payloads. It normalizes the budget when the model supports thinking.
func ApplyThinkingMetadata(payload []byte, metadata map[string]any, model string) []byte {
budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
// Use the alias from metadata if available, as it's registered in the global registry
// with thinking metadata; the upstream model name may not be registered.
lookupModel := util.ResolveOriginalModel(model, metadata)
// Determine which model to use for thinking support check.
// If the alias (lookupModel) is not in the registry, fall back to the upstream model.
thinkingModel := lookupModel
if !util.ModelSupportsThinking(lookupModel) && util.ModelSupportsThinking(model) {
thinkingModel = model
}
budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(thinkingModel, metadata)
if !ok || (budgetOverride == nil && includeOverride == nil) {
return payload
}
if !util.ModelSupportsThinking(model) {
if !util.ModelSupportsThinking(thinkingModel) {
return payload
}
if budgetOverride != nil {
norm := util.NormalizeThinkingBudget(model, *budgetOverride)
norm := util.NormalizeThinkingBudget(thinkingModel, *budgetOverride)
budgetOverride = &norm
}
return util.ApplyGeminiThinkingConfig(payload, budgetOverride, includeOverride)
}
// applyThinkingMetadataCLI applies thinking config from model suffix metadata (e.g., (high), (8192))
// ApplyThinkingMetadataCLI applies thinking config from model suffix metadata (e.g., (high), (8192))
// for Gemini CLI format payloads (nested under "request"). It normalizes the budget when the model supports thinking.
func applyThinkingMetadataCLI(payload []byte, metadata map[string]any, model string) []byte {
budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(model, metadata)
func ApplyThinkingMetadataCLI(payload []byte, metadata map[string]any, model string) []byte {
// Use the alias from metadata if available, as it's registered in the global registry
// with thinking metadata; the upstream model name may not be registered.
lookupModel := util.ResolveOriginalModel(model, metadata)
// Determine which model to use for thinking support check.
// If the alias (lookupModel) is not in the registry, fall back to the upstream model.
thinkingModel := lookupModel
if !util.ModelSupportsThinking(lookupModel) && util.ModelSupportsThinking(model) {
thinkingModel = model
}
budgetOverride, includeOverride, ok := util.ResolveThinkingConfigFromMetadata(thinkingModel, metadata)
if !ok || (budgetOverride == nil && includeOverride == nil) {
return payload
}
if !util.ModelSupportsThinking(model) {
if !util.ModelSupportsThinking(thinkingModel) {
return payload
}
if budgetOverride != nil {
norm := util.NormalizeThinkingBudget(model, *budgetOverride)
norm := util.NormalizeThinkingBudget(thinkingModel, *budgetOverride)
budgetOverride = &norm
}
return util.ApplyGeminiCLIThinkingConfig(payload, budgetOverride, includeOverride)