fix(gemini): resolve latency and error issues with model normalization and v1beta tool routing

internal/db/db.go

@@ -209,9 +209,9 @@ func (db *DB) RunMigrations() error {
 	}{
 		{"deepseek-auto", "heuristic", `["deepseek-chat","deepseek-reasoner"]`, "", nil, nil, nil},
 		{"openai-auto", "heuristic", `["gpt-4o-mini","gpt-4o"]`, "", nil, nil, nil},
-		{"gemini-auto", "heuristic", `["gemini-2.5-flash","gemini-2.5-pro"]`, "", nil, nil, nil},
+		{"gemini-auto", "heuristic", `["gemini-3.5-flash-lite","gemini-3.1-flash-lite","gemini-2.5-flash"]`, "", nil, nil, nil},
 		{"heavy-logic", "heuristic", `["grok-4.3","kimi-k2.6","deepseek-v4-pro"]`, "", nil, intPtr(9), strPtr("Complex Coding, Logic, Agents.")},
-		{"standard-pro", "heuristic", `["gpt-5.4-mini","gemini-3-flash-preview"]`, "", nil, intPtr(5), strPtr("General Assistant, Long Docs.")},
+		{"standard-pro", "heuristic", `["gpt-5.4-mini","gemini-3.5-flash-lite"]`, "", nil, intPtr(5), strPtr("General Assistant, Long Docs.")},
 		{"fast-flow", "heuristic", `["deepseek-v4-flash","gpt-5.4-nano"]`, "", nil, intPtr(2), strPtr("Classification, JSON, Basic Q&A.")},
 		{"dispatcher", "classifier", `["fast-flow","standard-pro","heavy-logic"]`, "gpt-5.4-nano", intPtr(10), nil, strPtr("Auto-dispatches to tier groups by complexity.")},
 	}

internal/providers/gemini.go

@@ -202,15 +202,7 @@ func (p *GeminiProvider) ResponsesStream(ctx context.Context, req *models.Respon
 }
 
 func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.UnifiedRequest) (*models.ChatCompletionResponse, error) {
-	// Map deprecated or preview model names to active equivalents
+	req.Model = normalizeGeminiModel(req.Model)
-	switch req.Model {
-	case "gemini-2.0-flash":
-		req.Model = "gemini-2.5-flash"
-	case "gemini-3-flash":
-		req.Model = "gemini-3-flash-preview"
-	case "gemini-3-pro":
-		req.Model = "gemini-3-pro-preview"
-	}
 
 	// Gemini mapping
 	var contents []GeminiContent
@@ -273,7 +265,7 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 			}
 
 			if foundAny {
-				contents = append(contents, GeminiContent{Role: "function", Parts: functionParts})
+				contents = append(contents, GeminiContent{Role: "user", Parts: functionParts})
 				i = j - 1 // Advance outer loop past the tool messages we consumed
 			} else {
 				// If no tool results found but assistant made calls, Gemini WILL error.
@@ -364,8 +356,9 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 	if strings.Contains(lowerModel, "preview") ||
 		strings.Contains(lowerModel, "thinking") ||
 		strings.Contains(lowerModel, "gemini-") ||
-		hasMappedTools {
+		hasMappedTools ||
-		// Use v1beta for preview, newer models, or when using tools
+		hasHistoryToolCalls(contents) {
+		// Use v1beta for preview, newer models, tool use, or historical tool calls
 		if !strings.Contains(baseURL, "v1beta") {
 			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)
 		}
@@ -478,15 +471,7 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 }
 
 func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.UnifiedRequest) (<-chan *models.ChatCompletionStreamResponse, error) {
-	// Map deprecated or preview model names to active equivalents
+	req.Model = normalizeGeminiModel(req.Model)
-	switch req.Model {
-	case "gemini-2.0-flash":
-		req.Model = "gemini-2.5-flash"
-	case "gemini-3-flash":
-		req.Model = "gemini-3-flash-preview"
-	case "gemini-3-pro":
-		req.Model = "gemini-3-pro-preview"
-	}
 
 	// Simplified Gemini mapping
 	var contents []GeminiContent
@@ -535,7 +520,7 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 			}
 
 			if foundAny {
-				contents = append(contents, GeminiContent{Role: "function", Parts: functionParts})
+				contents = append(contents, GeminiContent{Role: "user", Parts: functionParts})
 				i = j - 1
 			}
 			continue
@@ -617,8 +602,9 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 	if strings.Contains(lowerModel, "preview") ||
 		strings.Contains(lowerModel, "thinking") ||
 		strings.Contains(lowerModel, "gemini-") ||
-		hasMappedTools {
+		hasMappedTools ||
-		// Use v1beta for preview, newer models, or when using tools
+		hasHistoryToolCalls(contents) {
+		// Use v1beta for preview, newer models, tool use, or historical tool calls
 		if !strings.Contains(baseURL, "v1beta") {
 			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)
 		}
@@ -748,3 +734,30 @@ func resolveToolName(toolMsg models.UnifiedMessage, toolCalls []models.ToolCall,
 	return "unknown_function"
 }
 
+func normalizeGeminiModel(model string) string {
+	switch model {
+	case "gemini-2.0-flash", "gemini-1.5-flash":
+		return "gemini-3.5-flash-lite"
+	case "gemini-3-flash", "gemini-3-flash-preview":
+		return "gemini-3.5-flash-lite"
+	case "gemini-3-pro", "gemini-3-pro-preview", "gemini-1.5-pro":
+		return "gemini-2.5-pro"
+	default:
+		return model
+	}
+}
+
+func hasHistoryToolCalls(contents []GeminiContent) bool {
+	for _, c := range contents {
+		if c.Role == "function" {
+			return true
+		}
+		for _, p := range c.Parts {
+			if p.FunctionCall != nil || p.FunctionResponse != nil {
+				return true
+			}
+		}
+	}
+	return false
+}
+