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

Refactors the reasoning effort conversion logic for Gemini models.
The update specifically addresses how `reasoning_effort` is translated into Gemini 3 specific thinking configurations (`thinkingLevel`, `includeThoughts`) and ensures that numeric budgets are not incorrectly applied to level-based models.

Changes include:
- Differentiating conversion logic for Gemini 3 models versus other models.
- Handling `none`, `auto`, and validated thinking levels for Gemini 3.
- Maintaining existing conversion for models not using discrete thinking levels.

internal/translator/antigravity/openai/chat-completions/antigravity_openai_request.go

@@ -39,8 +39,23 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
 	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	hasOfficialThinking := re.Exists()
-	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
-		out = util.ApplyReasoningEffortToGeminiCLI(out, re.String())
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		effort := strings.ToLower(strings.TrimSpace(re.String()))
+		if util.IsGemini3Model(modelName) {
+			switch effort {
+			case "none":
+				out, _ = sjson.DeleteBytes(out, "request.generationConfig.thinkingConfig")
+			case "auto":
+				includeThoughts := true
+				out = util.ApplyGeminiCLIThinkingLevel(out, "", &includeThoughts)
+			default:
+				if level, ok := util.ValidateGemini3ThinkingLevel(modelName, effort); ok {
+					out = util.ApplyGeminiCLIThinkingLevel(out, level, nil)
+				}
+			}
+		} else if !util.ModelUsesThinkingLevels(modelName) {
+			out = util.ApplyReasoningEffortToGeminiCLI(out, effort)
+		}
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)

internal/translator/gemini/openai/chat-completions/gemini_openai_request.go

@@ -37,12 +37,28 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
 
 	// Reasoning effort -> thinkingBudget/include_thoughts
 	// Note: OpenAI official fields take precedence over extra_body.google.thinking_config
-	// Only convert for models that use numeric budgets (not discrete levels) to avoid
-	// incorrectly applying thinkingBudget for level-based models like gpt-5.
+	// Only apply numeric budgets for models that use budgets (not discrete levels) to avoid
+	// incorrectly applying thinkingBudget for level-based models like gpt-5. Gemini 3 models
+	// use thinkingLevel/includeThoughts instead.
 	re := gjson.GetBytes(rawJSON, "reasoning_effort")
 	hasOfficialThinking := re.Exists()
-	if hasOfficialThinking && util.ModelSupportsThinking(modelName) && !util.ModelUsesThinkingLevels(modelName) {
-		out = util.ApplyReasoningEffortToGemini(out, re.String())
+	if hasOfficialThinking && util.ModelSupportsThinking(modelName) {
+		effort := strings.ToLower(strings.TrimSpace(re.String()))
+		if util.IsGemini3Model(modelName) {
+			switch effort {
+			case "none":
+				out, _ = sjson.DeleteBytes(out, "generationConfig.thinkingConfig")
+			case "auto":
+				includeThoughts := true
+				out = util.ApplyGeminiThinkingLevel(out, "", &includeThoughts)
+			default:
+				if level, ok := util.ValidateGemini3ThinkingLevel(modelName, effort); ok {
+					out = util.ApplyGeminiThinkingLevel(out, level, nil)
+				}
+			}
+		} else if !util.ModelUsesThinkingLevels(modelName) {
+			out = util.ApplyReasoningEffortToGemini(out, effort)
+		}
 	}
 
 	// Cherry Studio extension extra_body.google.thinking_config (effective only when official fields are absent)

sdk/auth/filestore.go

@@ -72,7 +72,9 @@ func (s *FileTokenStore) Save(ctx context.Context, auth *cliproxyauth.Auth) (str
 			return "", fmt.Errorf("auth filestore: marshal metadata failed: %w", errMarshal)
 		}
 		if existing, errRead := os.ReadFile(path); errRead == nil {
-			if jsonEqual(existing, raw) {
+			// Use metadataEqualIgnoringTimestamps to skip writes when only timestamp fields change.
+			// This prevents the token refresh loop caused by timestamp/expired/expires_in changes.
+			if metadataEqualIgnoringTimestamps(existing, raw) {
 				return path, nil
 			}
 		} else if errRead != nil && !os.IsNotExist(errRead) {
@@ -264,6 +266,8 @@ func (s *FileTokenStore) baseDirSnapshot() string {
 	return s.baseDir
 }
 
+// DEPRECATED: Use metadataEqualIgnoringTimestamps for comparing auth metadata.
+// This function is kept for backward compatibility but can cause refresh loops. 
 func jsonEqual(a, b []byte) bool {
 	var objA any
 	var objB any
@@ -276,6 +280,32 @@ func jsonEqual(a, b []byte) bool {
 	return deepEqualJSON(objA, objB)
 }
 
+// metadataEqualIgnoringTimestamps compares two metadata JSON blobs,
+// ignoring fields that change on every refresh but don't affect functionality.
+// This prevents unnecessary file writes that would trigger watcher events and
+// create refresh loops.
+func metadataEqualIgnoringTimestamps(a, b []byte) bool {
+	var objA, objB map[string]any
+	if err := json.Unmarshal(a, &objA); err != nil {
+		return false
+	}
+	if err := json.Unmarshal(b, &objB); err != nil {
+		return false
+	}
+
+	// Fields to ignore: these change on every refresh but don't affect authentication logic.
+	// - timestamp, expired, expires_in, last_refresh: time-related fields that change on refresh
+	// - access_token: Google OAuth returns a new access_token on each refresh, this is expected
+	//   and shouldn't trigger file writes (the new token will be fetched again when needed)
+	ignoredFields := []string{"timestamp", "expired", "expires_in", "last_refresh", "access_token"}
+	for _, field := range ignoredFields {
+		delete(objA, field)
+		delete(objB, field)
+	}
+
+	return deepEqualJSON(objA, objB)
+}
+
 func deepEqualJSON(a, b any) bool {
 	switch valA := a.(type) {
 	case map[string]any: