feat(ollama): improve configuration and dashboard integration

internal/providers/gemini.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 
 	"gophergate/internal/config"
 	"gophergate/internal/models"
@@ -29,7 +30,16 @@ func (p *GeminiProvider) Name() string {
 }
 
 type GeminiRequest struct {
-	Contents []GeminiContent `json:"contents"`
+	Contents         []GeminiContent         `json:"contents"`
+	GenerationConfig *GeminiGenerationConfig `json:"generationConfig,omitempty"`
+}
+
+type GeminiGenerationConfig struct {
+	Temperature     *float32 `json:"temperature,omitempty"`
+	TopP            *float32 `json:"topP,omitempty"`
+	TopK            *int     `json:"topK,omitempty"`
+	MaxOutputTokens *int     `json:"maxOutputTokens,omitempty"`
+	StopSequences   []string `json:"stopSequences,omitempty"`
 }
 
 type GeminiContent struct {
@@ -125,11 +135,43 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 		})
 	}
 
-	body := GeminiRequest{
-		Contents: contents,
+	genConfig := &GeminiGenerationConfig{}
+	if req.Temperature != nil {
+		t := float32(*req.Temperature)
+		genConfig.Temperature = &t
+	}
+	if req.TopP != nil {
+		tp := float32(*req.TopP)
+		genConfig.TopP = &tp
+	}
+	if req.TopK != nil {
+		tk := int(*req.TopK)
+		genConfig.TopK = &tk
+	}
+	if req.MaxTokens != nil {
+		mt := int(*req.MaxTokens)
+		genConfig.MaxOutputTokens = &mt
+	}
+	if len(req.Stop) > 0 {
+		genConfig.StopSequences = req.Stop
 	}
 
-	url := fmt.Sprintf("%s/models/%s:generateContent?key=%s", p.config.BaseURL, req.Model, p.apiKey)
+	body := GeminiRequest{
+		Contents:         contents,
+		GenerationConfig: genConfig,
+	}
+
+	baseURL := p.config.BaseURL
+	lowerModel := strings.ToLower(req.Model)
+	if strings.Contains(lowerModel, "preview") || strings.Contains(lowerModel, "3.1") || strings.Contains(lowerModel, "2.0") || strings.Contains(lowerModel, "thinking") {
+		// Use v1beta for preview and newer models
+		if !strings.Contains(baseURL, "v1beta") {
+			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)
+		}
+	}
+
+	url := fmt.Sprintf("%s/models/%s:generateContent?key=%s", baseURL, req.Model, p.apiKey)
+	fmt.Printf("[Gemini] POST %s\n", url)
 
 	resp, err := p.client.R().
 		SetContext(ctx).
@@ -219,12 +261,44 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 		})
 	}
 
+	genConfig := &GeminiGenerationConfig{}
+	if req.Temperature != nil {
+		t := float32(*req.Temperature)
+		genConfig.Temperature = &t
+	}
+	if req.TopP != nil {
+		tp := float32(*req.TopP)
+		genConfig.TopP = &tp
+	}
+	if req.TopK != nil {
+		tk := int(*req.TopK)
+		genConfig.TopK = &tk
+	}
+	if req.MaxTokens != nil {
+		mt := int(*req.MaxTokens)
+		genConfig.MaxOutputTokens = &mt
+	}
+	if len(req.Stop) > 0 {
+		genConfig.StopSequences = req.Stop
+	}
+
 	body := GeminiRequest{
-		Contents: contents,
+		Contents:         contents,
+		GenerationConfig: genConfig,
+	}
+
+	baseURL := p.config.BaseURL
+	lowerModel := strings.ToLower(req.Model)
+	if strings.Contains(lowerModel, "preview") || strings.Contains(lowerModel, "3.1") || strings.Contains(lowerModel, "2.0") || strings.Contains(lowerModel, "thinking") {
+		// Use v1beta for preview and newer models
+		if !strings.Contains(baseURL, "v1beta") {
+			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)
+		}
 	}
 
 	// Use streamGenerateContent for streaming
-	url := fmt.Sprintf("%s/models/%s:streamGenerateContent?key=%s", p.config.BaseURL, req.Model, p.apiKey)
+	url := fmt.Sprintf("%s/models/%s:streamGenerateContent?key=%s", baseURL, req.Model, p.apiKey)
+	fmt.Printf("[Gemini-Stream] POST %s\n", url)
 
 	resp, err := p.client.R().
 		SetContext(ctx).