chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-19 04:40:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(executor): centralize default thinking config

Browse Source
This commit is contained in:
hkfires
2025-12-09 13:23:50 +08:00
parent 6a66b6801a
commit 9b202b6c1c
9 changed files with 52 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
internal/runtime/executor/aistudio_executor.go
View File

@@ -309,6 +309,7 @@ func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
to := sdktranslator.FromString("gemini") to := sdktranslator.FromString("gemini")
payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream) payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
payload = applyThinkingMetadata(payload, req.Metadata, req.Model) payload = applyThinkingMetadata(payload, req.Metadata, req.Model)
payload = util.ApplyDefaultThinkingIfNeeded(req.Model, payload)
payload = util.ConvertThinkingLevelToBudget(payload) payload = util.ConvertThinkingLevelToBudget(payload)
payload = util.NormalizeGeminiThinkingBudget(req.Model, payload) payload = util.NormalizeGeminiThinkingBudget(req.Model, payload)
payload = util.StripThinkingConfigIfUnsupported(req.Model, payload) payload = util.StripThinkingConfigIfUnsupported(req.Model, payload)

2
internal/runtime/executor/antigravity_executor.go
View File

@@ -77,6 +77,7 @@ func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Au
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false) 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.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
translated = normalizeAntigravityThinking(req.Model, translated) translated = normalizeAntigravityThinking(req.Model, translated)
baseURLs := antigravityBaseURLFallbackOrder(auth) baseURLs := antigravityBaseURLFallbackOrder(auth)
@@ -171,6 +172,7 @@ func (e *AntigravityExecutor) ExecuteStream(ctx context.Context, auth *cliproxya
translated := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true) 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.ApplyDefaultThinkingIfNeededCLI(req.Model, translated)
translated = normalizeAntigravityThinking(req.Model, translated) translated = normalizeAntigravityThinking(req.Model, translated)
baseURLs := antigravityBaseURLFallbackOrder(auth) baseURLs := antigravityBaseURLFallbackOrder(auth)

2
internal/runtime/executor/gemini_cli_executor.go
View File

@@ -64,6 +64,7 @@ func (e *GeminiCLIExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth
to := sdktranslator.FromString("gemini-cli") to := sdktranslator.FromString("gemini-cli")
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false) 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.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload) basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload) basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload) basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)
@@ -200,6 +201,7 @@ func (e *GeminiCLIExecutor) ExecuteStream(ctx context.Context, auth *cliproxyaut
to := sdktranslator.FromString("gemini-cli") to := sdktranslator.FromString("gemini-cli")
basePayload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true) 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.ApplyDefaultThinkingIfNeededCLI(req.Model, basePayload)
basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload) basePayload = util.NormalizeGeminiCLIThinkingBudget(req.Model, basePayload)
basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload) basePayload = util.StripThinkingConfigIfUnsupported(req.Model, basePayload)
basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload) basePayload = fixGeminiCLIImageAspectRatio(req.Model, basePayload)

2
internal/runtime/executor/gemini_executor.go
View File

@@ -80,6 +80,7 @@ func (e *GeminiExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
to := sdktranslator.FromString("gemini") to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false) body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
body = applyThinkingMetadata(body, req.Metadata, req.Model) body = applyThinkingMetadata(body, req.Metadata, req.Model)
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)
@@ -170,6 +171,7 @@ func (e *GeminiExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
to := sdktranslator.FromString("gemini") to := sdktranslator.FromString("gemini")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true) body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), true)
body = applyThinkingMetadata(body, req.Metadata, req.Model) body = applyThinkingMetadata(body, req.Metadata, req.Model)
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)

4
internal/runtime/executor/gemini_vertex_executor.go
View File

@@ -296,6 +296,7 @@ func (e *GeminiVertexExecutor) executeWithServiceAccount(ctx context.Context, au
} }
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride) body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
} }
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)
@@ -392,6 +393,7 @@ func (e *GeminiVertexExecutor) executeWithAPIKey(ctx context.Context, auth *clip
} }
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride) body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
} }
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)
@@ -489,6 +491,7 @@ func (e *GeminiVertexExecutor) executeStreamWithServiceAccount(ctx context.Conte
} }
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride) body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
} }
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)
@@ -602,6 +605,7 @@ func (e *GeminiVertexExecutor) executeStreamWithAPIKey(ctx context.Context, auth
} }
body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride) body = util.ApplyGeminiThinkingConfig(body, budgetOverride, includeOverride)
} }
body = util.ApplyDefaultThinkingIfNeeded(req.Model, body)
body = util.NormalizeGeminiThinkingBudget(req.Model, body) body = util.NormalizeGeminiThinkingBudget(req.Model, body)
body = util.StripThinkingConfigIfUnsupported(req.Model, body) body = util.StripThinkingConfigIfUnsupported(req.Model, body)
body = fixGeminiImageAspectRatio(req.Model, body) body = fixGeminiImageAspectRatio(req.Model, body)

9
internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go
View File

@@ -102,15 +102,6 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
} }
} }
// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
// This matches the official Gemini CLI behavior which always sends:
// { thinkingBudget: -1, includeThoughts: true }
// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
if !gjson.GetBytes(out, "request.generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
}
// Temperature/top_p/top_k/max_tokens // Temperature/top_p/top_k/max_tokens
if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number { if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number {
out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num) out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num)

9
internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_request.go
View File

@@ -88,15 +88,6 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
} }
} }
// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
// This matches the official Gemini CLI behavior which always sends:
// { thinkingBudget: -1, includeThoughts: true }
// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
if !gjson.GetBytes(out, "request.generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
out, _ = sjson.SetBytes(out, "request.generationConfig.thinkingConfig.include_thoughts", true)
}
// Temperature/top_p/top_k // Temperature/top_p/top_k
if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number { if tr := gjson.GetBytes(rawJSON, "temperature"); tr.Exists() && tr.Type == gjson.Number {
out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num) out, _ = sjson.SetBytes(out, "request.generationConfig.temperature", tr.Num)

10
internal/translator/gemini/openai/responses/gemini_openai-responses_request.go
View File

@@ -437,16 +437,6 @@ func ConvertOpenAIResponsesRequestToGemini(modelName string, inputRawJSON []byte
} }
} }
// For gemini-3-pro-preview, always send default thinkingConfig when none specified.
// This matches the official Gemini CLI behavior which always sends:
// { thinkingBudget: -1, includeThoughts: true }
// See: ai-gemini-cli/packages/core/src/config/defaultModelConfigs.ts
if !gjson.Get(out, "generationConfig.thinkingConfig").Exists() && modelName == "gemini-3-pro-preview" {
out, _ = sjson.Set(out, "generationConfig.thinkingConfig.thinkingBudget", -1)
out, _ = sjson.Set(out, "generationConfig.thinkingConfig.include_thoughts", true)
// log.Debugf("Applied default thinkingConfig for gemini-3-pro-preview (matches Gemini CLI): thinkingBudget=-1, include_thoughts=true")
}
result := []byte(out) result := []byte(out)
result = common.AttachDefaultSafetySettings(result, "safetySettings") result = common.AttachDefaultSafetySettings(result, "safetySettings")
return result return result

41
internal/util/gemini_thinking.go
View File

@@ -207,6 +207,47 @@ func GeminiThinkingFromMetadata(metadata map[string]any) (*int, *bool, bool) {
return budgetPtr, includePtr, matched return budgetPtr, includePtr, matched
} }
// modelsWithDefaultThinking lists models that should have thinking enabled by default
// when no explicit thinkingConfig is provided.
var modelsWithDefaultThinking = map[string]bool{
"gemini-3-pro-preview": true,
}
// ModelHasDefaultThinking returns true if the model should have thinking enabled by default.
func ModelHasDefaultThinking(model string) bool {
return modelsWithDefaultThinking[model]
}
// ApplyDefaultThinkingIfNeeded injects default thinkingConfig for models that require it.
// For standard Gemini API format (generationConfig.thinkingConfig path).
// Returns the modified body if thinkingConfig was added, otherwise returns the original.
func ApplyDefaultThinkingIfNeeded(model string, body []byte) []byte {
if !ModelHasDefaultThinking(model) {
return body
}
if gjson.GetBytes(body, "generationConfig.thinkingConfig").Exists() {
return body
}
updated, _ := sjson.SetBytes(body, "generationConfig.thinkingConfig.thinkingBudget", -1)
updated, _ = sjson.SetBytes(updated, "generationConfig.thinkingConfig.include_thoughts", true)
return updated
}
// ApplyDefaultThinkingIfNeededCLI injects default thinkingConfig for models that require it.
// For Gemini CLI API format (request.generationConfig.thinkingConfig path).
// Returns the modified body if thinkingConfig was added, otherwise returns the original.
func ApplyDefaultThinkingIfNeededCLI(model string, body []byte) []byte {
if !ModelHasDefaultThinking(model) {
return body
}
if gjson.GetBytes(body, "request.generationConfig.thinkingConfig").Exists() {
return body
}
updated, _ := sjson.SetBytes(body, "request.generationConfig.thinkingConfig.thinkingBudget", -1)
updated, _ = sjson.SetBytes(updated, "request.generationConfig.thinkingConfig.include_thoughts", true)
return updated
}
// StripThinkingConfigIfUnsupported removes thinkingConfig from the request body // StripThinkingConfigIfUnsupported removes thinkingConfig from the request body
// when the target model does not advertise Thinking capability. It cleans both // when the target model does not advertise Thinking capability. It cleans both
// standard Gemini and Gemini CLI JSON envelopes. This acts as a final safety net // standard Gemini and Gemini CLI JSON envelopes. This acts as a final safety net