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

Author: luispater

internal/registry/model_definitions.go

@@ -222,6 +222,7 @@ func GetGeminiModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
 		},
 	}
 }
@@ -301,6 +302,7 @@ func GetGeminiVertexModels() []*ModelInfo {
 			InputTokenLimit:            1048576,
 			OutputTokenLimit:           65536,
 			SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
+			Thinking:                   &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
 		},
 	}
 }

internal/runtime/executor/antigravity_executor.go

@@ -17,6 +17,7 @@ import (
 	"github.com/google/uuid"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/config"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
+	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	cliproxyauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
 	cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
 	sdktranslator "github.com/router-for-me/CLIProxyAPI/v6/sdk/translator"
@@ -58,6 +59,20 @@ func (e *AntigravityExecutor) Identifier() string { return antigravityAuthType }
 // PrepareRequest implements ProviderExecutor.
 func (e *AntigravityExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error { return nil }
 
+// applyThinkingMetadata applies thinking config from model suffix metadata (e.g., -reasoning, -thinking-N).
+// It trusts user intent when suffix is used, even if registry doesn't have Thinking metadata.
+func applyThinkingMetadata(translated []byte, metadata map[string]any, model string) []byte {
+	budgetOverride, includeOverride, ok := util.GeminiThinkingFromMetadata(metadata)
+	if !ok {
+		return translated
+	}
+	if budgetOverride != nil && util.ModelSupportsThinking(model) {
+		norm := util.NormalizeThinkingBudget(model, *budgetOverride)
+		budgetOverride = &norm
+	}
+	return util.ApplyGeminiCLIThinkingConfig(translated, budgetOverride, includeOverride)
+}
+
 // Execute handles non-streaming requests via the antigravity generate endpoint.
 func (e *AntigravityExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
 	token, updatedAuth, errToken := e.ensureAccessToken(ctx, auth)
@@ -75,6 +90,8 @@ 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 = applyThinkingMetadata(translated, req.Metadata, req.Model)
+
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 
@@ -166,6 +183,8 @@ 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 = applyThinkingMetadata(translated, req.Metadata, req.Model)
+
 	baseURLs := antigravityBaseURLFallbackOrder(auth)
 	httpClient := newProxyAwareHTTPClient(ctx, e.cfg, auth, 0)
 

internal/util/gemini_thinking.go

@@ -34,6 +34,15 @@ func ParseGeminiThinkingSuffix(model string) (string, *int, *bool, bool) {
 		return base, &budgetValue, &include, true
 	}
 
+	// Handle "-reasoning" suffix: enables thinking with dynamic budget (-1)
+	// Maps: gemini-2.5-flash-reasoning -> gemini-2.5-flash with thinkingBudget=-1
+	if strings.HasSuffix(lower, "-reasoning") {
+		base := model[:len(model)-len("-reasoning")]
+		budgetValue := -1 // Dynamic budget
+		include := true
+		return base, &budgetValue, &include, true
+	}
+
 	idx := strings.LastIndex(lower, "-thinking-")
 	if idx == -1 {
 		return model, nil, nil, false