fix: resolve retired/preview gemini model routing and test configuration errors

.gitignore

@@ -16,3 +16,5 @@ server.pid
 /target
 nohup.out
 *.bak
+.antigravitycli/
+

README.md

@@ -239,7 +239,7 @@ Pre-seeded groups:
 | `dispatcher` | - | classifier | fast-flow, standard-pro, heavy-logic | Auto-dispatches by complexity |
 | `deepseek-auto` | - | heuristic | deepseek-chat, deepseek-reasoner | Legacy provider group |
 | `openai-auto` | - | heuristic | gpt-4o-mini, gpt-4o | Legacy provider group |
-| `gemini-auto` | - | heuristic | gemini-2.0-flash, gemini-2.5-pro | Legacy provider group |
+| `gemini-auto` | - | heuristic | gemini-2.5-flash, gemini-2.5-pro | Legacy provider group |
 
 ### Image Generation (DALL-E / Imagen)
 

deploy.sh

@@ -1,23 +1,25 @@
 #!/bin/bash
 
-# Define the service name/path for easy updates
+set -e
+
 BINARY_NAME="gophergate"
 SOURCE_PATH="./cmd/gophergate/main.go"
 
-echo "Stopping existing $BINARY_NAME processes..."
-# Using pkill; || true ensures the script continues even if no process was found
-pkill -9 "$BINARY_NAME" || echo "No running process found."
-
 echo "Pulling latest changes from git..."
+git stash || true
 git pull
 
 echo "Building the application..."
-if go build -o "$BINARY_NAME" "$SOURCE_PATH"; then
-    echo "Build successful. Starting $BINARY_NAME in the background..."
-    # Launch with nohup and redirect output to a log file
-    nohup "./$BINARY_NAME" > gophergate.log 2>&1 &
-    echo "Service started. PID: $!"
+go build -o "$BINARY_NAME" "$SOURCE_PATH"
+
+echo "Restarting service..."
+systemctl restart gophergate
+
+sleep 2
+if systemctl is-active --quiet gophergate; then
+    echo "Deploy complete. Service is running."
+    systemctl status gophergate --no-pager | head -5
 else
-    echo "Build failed! Keeping the previous state."
+    echo "Service failed to start! Check: journalctl -u gophergate -n 20"
     exit 1
 fi

internal/config/config.go

@@ -106,7 +106,7 @@ func Load() (*Config, error) {
 
 	v.SetDefault("providers.gemini.api_key_env", "GEMINI_API_KEY")
 	v.SetDefault("providers.gemini.base_url", "https://generativelanguage.googleapis.com/v1")
-	v.SetDefault("providers.gemini.default_model", "gemini-2.0-flash")
+	v.SetDefault("providers.gemini.default_model", "gemini-2.5-flash")
 	v.SetDefault("providers.gemini.enabled", true)
 
 	v.SetDefault("providers.deepseek.api_key_env", "DEEPSEEK_API_KEY")
@@ -116,7 +116,7 @@ func Load() (*Config, error) {
 
 	v.SetDefault("providers.moonshot.api_key_env", "MOONSHOT_API_KEY")
 	v.SetDefault("providers.moonshot.base_url", "https://api.moonshot.ai/v1")
-	v.SetDefault("providers.moonshot.default_model", "kimi-k2.5")
+	v.SetDefault("providers.moonshot.default_model", "kimi-k2.7-code")
 	v.SetDefault("providers.moonshot.enabled", true)
 
 	v.SetDefault("providers.grok.api_key_env", "GROK_API_KEY")

internal/db/db.go

@@ -209,7 +209,7 @@ 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-2.0-flash","gemini-2.5-pro"]`, "", nil, nil, nil},
+		{"gemini-auto", "heuristic", `["gemini-2.5-flash","gemini-2.5-pro"]`, "", 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.")},
 		{"fast-flow", "heuristic", `["deepseek-v4-flash","gpt-5.4-nano"]`, "", nil, intPtr(2), strPtr("Classification, JSON, Basic Q&A.")},

internal/providers/gemini.go

@@ -201,6 +201,16 @@ 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
+	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
 
@@ -354,7 +364,10 @@ func (p *GeminiProvider) ChatCompletion(ctx context.Context, req *models.Unified
 
 	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") || hasMappedTools {
+	if strings.Contains(lowerModel, "preview") ||
+		strings.Contains(lowerModel, "thinking") ||
+		strings.Contains(lowerModel, "gemini-") ||
+		hasMappedTools {
 		// Use v1beta for preview, newer models, or when using tools
 		if !strings.Contains(baseURL, "v1beta") {
 			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)
@@ -468,6 +481,16 @@ 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
+	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
 	for i := 0; i < len(req.Messages); i++ {
@@ -598,7 +621,10 @@ func (p *GeminiProvider) ChatCompletionStream(ctx context.Context, req *models.U
 
 	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") || hasMappedTools {
+	if strings.Contains(lowerModel, "preview") ||
+		strings.Contains(lowerModel, "thinking") ||
+		strings.Contains(lowerModel, "gemini-") ||
+		hasMappedTools {
 		// Use v1beta for preview, newer models, or when using tools
 		if !strings.Contains(baseURL, "v1beta") {
 			baseURL = strings.Replace(baseURL, "/v1", "/v1beta", 1)

internal/providers/moonshot.go

@@ -44,6 +44,11 @@ func (p *MoonshotProvider) ChatCompletion(ctx context.Context, req *models.Unifi
 			body["max_completion_tokens"] = maxTokens
 		}
 	}
+	if strings.Contains(strings.ToLower(req.Model), "kimi-k2.6") {
+		if _, ok := body["temperature"]; ok {
+			body["temperature"] = 1.0
+		}
+	}
 
 	baseURL := strings.TrimRight(p.config.BaseURL, "/")
 
@@ -90,6 +95,11 @@ func (p *MoonshotProvider) ChatCompletionStream(ctx context.Context, req *models
 			body["max_completion_tokens"] = maxTokens
 		}
 	}
+	if strings.Contains(strings.ToLower(req.Model), "kimi-k2.6") {
+		if _, ok := body["temperature"]; ok {
+			body["temperature"] = 1.0
+		}
+	}
 
 	baseURL := strings.TrimRight(p.config.BaseURL, "/")
 

internal/router/heuristic.go

@@ -26,12 +26,13 @@ type ConditionRule struct {
 
 // Conditions defines the matching parameters for a rule.
 type Conditions struct {
-	AnyOfTags           []string `json:"any_of_tags,omitempty"`
-	MaxInputTokensLt    *int     `json:"max_input_tokens_lt,omitempty"`
-	RequiresReasoning   *bool    `json:"requires_reasoning,omitempty"`
-	RequiresToolCalling *bool    `json:"requires_tool_calling,omitempty"`
-	HasMultimodalInput  *bool    `json:"has_multimodal_input,omitempty"`
-	IsDefaultFallback   *bool    `json:"is_default_fallback,omitempty"`
+	AnyOfTags             []string `json:"any_of_tags,omitempty"`
+	MaxInputTokensLt      *int     `json:"max_input_tokens_lt,omitempty"`
+	RequiresReasoning     *bool    `json:"requires_reasoning,omitempty"`
+	RequiresToolCalling   *bool    `json:"requires_tool_calling,omitempty"`
+	IsSoftwareDevelopment *bool    `json:"is_software_development,omitempty"`
+	HasMultimodalInput    *bool    `json:"has_multimodal_input,omitempty"`
+	IsDefaultFallback     *bool    `json:"is_default_fallback,omitempty"`
 }
 
 func routeHeuristic(group db.ModelGroup, targets []string, routeCtx *RouteContext) (*Decision, error) {
@@ -198,6 +199,13 @@ func matchConditions(cond Conditions, routeCtx *RouteContext) bool {
 		}
 	}
 
+	// Check software development flag
+	if cond.IsSoftwareDevelopment != nil {
+		if routeCtx.IsSoftwareDevelopment != *cond.IsSoftwareDevelopment {
+			return false
+		}
+	}
+
 	// Check multimodal flag
 	if cond.HasMultimodalInput != nil {
 		if routeCtx.HasMultimodalInput != *cond.HasMultimodalInput {

internal/router/heuristic_test.go

@@ -140,3 +140,65 @@ func TestRouteHeuristic_LegacyRules(t *testing.T) {
 		t.Fatalf("expected kimi-k2.6, got %s", dec2.SelectedModel)
 	}
 }
+
+func TestRouteHeuristic_SoftwareDevelopmentCondition(t *testing.T) {
+	targets := []string{
+		"gemini-3-flash",
+		"kimi-k2.7-code",
+		"deepseek-v4-pro",
+		"mimo-v2.5-pro",
+	}
+
+	rulesJSON := `[
+		{
+			"rule_id": "agentic_code_and_tools",
+			"conditions": {
+				"requires_tool_calling": true,
+				"is_software_development": true
+			},
+			"primary_model": "kimi-k2.7-code",
+			"fallback_model": "deepseek-v4-pro"
+		},
+		{
+			"rule_id": "agentic_general_tasks",
+			"conditions": {
+				"requires_tool_calling": true
+			},
+			"primary_model": "mimo-v2.5-pro"
+		}
+	]`
+
+	group := db.ModelGroup{
+		ID:             "dustins_stack",
+		Strategy:       "heuristic",
+		HeuristicRules: &rulesJSON,
+	}
+
+	// 1. Tool calling + Software dev should route to kimi-k2.7-code
+	ctx1 := &RouteContext{
+		UserMessage:           "Write a python script to parse logs",
+		RequiresToolCalling:   true,
+		IsSoftwareDevelopment: true,
+	}
+	dec1, err := routeHeuristic(group, targets, ctx1)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if dec1.SelectedModel != "kimi-k2.7-code" {
+		t.Fatalf("expected kimi-k2.7-code, got %s", dec1.SelectedModel)
+	}
+
+	// 2. Tool calling but NOT Software dev should route to mimo-v2.5-pro
+	ctx2 := &RouteContext{
+		UserMessage:           "Search the web for weather in New York",
+		RequiresToolCalling:   true,
+		IsSoftwareDevelopment: false,
+	}
+	dec2, err := routeHeuristic(group, targets, ctx2)
+	if err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+	if dec2.SelectedModel != "mimo-v2.5-pro" {
+		t.Fatalf("expected mimo-v2.5-pro, got %s (reason: %s)", dec2.SelectedModel, dec2.Reason)
+	}
+}

internal/router/router.go

@@ -18,12 +18,13 @@ type Decision struct {
 
 // RouteContext holds metadata of the request to evaluate condition rules.
 type RouteContext struct {
-	UserMessage         string   `json:"user_message"`
-	InputTokens         int      `json:"input_tokens"`
-	HasMultimodalInput  bool     `json:"has_multimodal_input"`
-	RequiresToolCalling bool     `json:"requires_tool_calling"`
-	RequiresReasoning   bool     `json:"requires_reasoning"`
-	Tags                []string `json:"tags"`
+	UserMessage           string   `json:"user_message"`
+	InputTokens           int      `json:"input_tokens"`
+	HasMultimodalInput    bool     `json:"has_multimodal_input"`
+	RequiresToolCalling   bool     `json:"requires_tool_calling"`
+	RequiresReasoning     bool     `json:"requires_reasoning"`
+	IsSoftwareDevelopment bool     `json:"is_software_development"`
+	Tags                  []string `json:"tags"`
 }
 
 // ClassifierFunc is the callback for classifier-based routing.

internal/server/models_config.go

@@ -49,6 +49,7 @@ func (s *Server) handleGetModels(c *gin.Context) {
 
 	var result []gin.H
 	s.registryMu.RLock()
+	defer s.registryMu.RUnlock()
 	if s.registry != nil {
 		for pID, pInfo := range s.registry.Providers {
 			proxyProvider, allowed := allowedRegistryProviders[pID]
@@ -208,6 +209,7 @@ func (s *Server) handleUpdateModel(c *gin.Context) {
 			}
 		}
 	}
+	s.registryMu.RUnlock()
 
 	_, err := s.database.Exec(`
 		INSERT INTO model_configs (id, provider_id, enabled, prompt_cost_per_m, completion_cost_per_m, cache_read_cost_per_m, cache_write_cost_per_m, mapping)

internal/server/providers_admin.go

@@ -226,11 +226,11 @@ func (s *Server) handleTestProvider(c *gin.Context) {
 
 	// Adjust model for non-openai providers
 	if name == "gemini" {
-		testReq.Model = "gemini-2.0-flash"
+		testReq.Model = "gemini-2.5-flash"
 	} else if name == "deepseek" {
 		testReq.Model = "deepseek-chat"
 	} else if name == "moonshot" {
-		testReq.Model = "kimi-k2.5"
+		testReq.Model = "kimi-k2.7-code"
 	} else if name == "grok" {
 		testReq.Model = "grok-4-1-fast-non-reasoning"
 	} else if name == "xiaomi" {

internal/server/routing_test.go

@@ -0,0 +1,31 @@
+package server
+
+import "testing"
+
+func TestIsSoftwareDevelopment(t *testing.T) {
+	tests := []struct {
+		message  string
+		expected bool
+	}{
+		{"can you check the logs? it looks like a lot of requests are being routed to kimi-k2.7-code when they don't need to be", false},
+		{"it looks like its still routing to kimi when it shouldn't need to", false},
+		{"Write a python script to parse logs", true},
+		{"Search the web for weather in New York", false},
+		{"How to build a compiler in Go", true},
+		{"Check my vscode config", false},
+		{"Let's decode this barcode", false},
+		{"go ahead and email both docxs and the ppt to kayla\n\n<memory-context>... HELPipedia_Telethon_Speaker_Script.docx ... mental health program specialist ...", false},
+		{"academic program development", false},
+		{"write a script for the video presentation", false},
+		{"How to write a bash script", true},
+		{"refactor this sql query", true},
+		{"can you organize Downloads and Documents real quick?\n\n<memory-context>\nCLI wrapper: ~/Projects/rag-engine/rag (bash script activating .venv). Python venv@~/Projects/rag-engine/.venv/.\n</memory-context>", false},
+	}
+
+	for _, tt := range tests {
+		result := isSoftwareDevelopment(tt.message)
+		if result != tt.expected {
+			t.Errorf("isSoftwareDevelopment(%q) = %v; expected %v", tt.message, result, tt.expected)
+		}
+	}
+}

internal/server/server.go

@@ -1,12 +1,13 @@
 package server
 
 import (
-	"encoding/json"
 	"context"
+	"encoding/json"
 	"fmt"
 	"io"
 	"log"
 	"net/http"
+	"regexp"
 	"strings"
 	"sync"
 	"time"
@@ -57,7 +58,9 @@ func NewServer(cfg *config.Config, database *db.DB) *Server {
 		if err != nil {
 			fmt.Printf("Warning: Failed to fetch initial model registry: %v\n", err)
 		} else {
+			s.registryMu.Lock()
 			s.registry = registry
+			s.registryMu.Unlock()
 		}
 	}()
 
@@ -976,12 +979,14 @@ func (s *Server) buildRouteContextFromChat(req models.ChatCompletionRequest) *ro
 		strings.Contains(msgLower, "explain in detail")
 
 	routeCtx := &router.RouteContext{
-		UserMessage:         userMessage,
-		InputTokens:         inputTokens,
-		HasMultimodalInput:  hasMultimodal,
-		RequiresToolCalling: requiresToolCalling,
-		RequiresReasoning:   requiresReasoning,
+		UserMessage:           userMessage,
+		InputTokens:           inputTokens,
+		HasMultimodalInput:    hasMultimodal,
+		RequiresToolCalling:   requiresToolCalling,
+		RequiresReasoning:     requiresReasoning,
+		IsSoftwareDevelopment: isSoftwareDevelopment(userMessage),
 	}
+	log.Printf("[DEBUG] RouteContext built: msg=%q, IsSoftwareDevelopment=%v", userMessage, routeCtx.IsSoftwareDevelopment)
 	routeCtx.Tags = s.getRouteCtxTags(routeCtx)
 	return routeCtx
 }
@@ -1034,12 +1039,14 @@ func (s *Server) buildRouteContextFromResponses(req models.ResponsesRequest) *ro
 		strings.Contains(msgLower, "explain in detail")
 
 	routeCtx := &router.RouteContext{
-		UserMessage:         userMessage,
-		InputTokens:         inputTokens,
-		HasMultimodalInput:  hasMultimodal,
-		RequiresToolCalling: requiresToolCalling,
-		RequiresReasoning:   requiresReasoning,
+		UserMessage:           userMessage,
+		InputTokens:           inputTokens,
+		HasMultimodalInput:    hasMultimodal,
+		RequiresToolCalling:   requiresToolCalling,
+		RequiresReasoning:     requiresReasoning,
+		IsSoftwareDevelopment: isSoftwareDevelopment(userMessage),
 	}
+	log.Printf("[DEBUG] RouteContext built: msg=%q, IsSoftwareDevelopment=%v", userMessage, routeCtx.IsSoftwareDevelopment)
 	routeCtx.Tags = s.getRouteCtxTags(routeCtx)
 	return routeCtx
 }
@@ -1102,3 +1109,35 @@ func (s *Server) getRouteCtxTags(routeCtx *router.RouteContext) []string {
 
 	return tags
 }
+
+var (
+	modelStripRegex    = regexp.MustCompile(`(?i)\b[a-z0-9/._:-]*(code|coder|codex)[a-z0-9/._:-]*\b`)
+	memoryContextRegex = regexp.MustCompile(`(?s)<memory-context>.*?</memory-context>`)
+	softwareDevRegex   = regexp.MustCompile(`(?i)\b(code|coding|programmer|programming|software|refactor|refactoring|compile|compiling|compiler|git|github|debug|debugging|repository|repo|unittest|unit test|test suite|test case|test cases|pull request|merge conflict|syntax error|source code|python|golang|javascript|typescript|ruby|php|perl|swift|kotlin|scala|rustlang|bash|powershell|sql|script|snippet|api|endpoint|patch|diff)\b`)
+)
+
+func isSoftwareDevelopment(userMessage string) bool {
+	msgLower := strings.ToLower(userMessage)
+	sanitized := memoryContextRegex.ReplaceAllString(msgLower, "")
+	sanitized = modelStripRegex.ReplaceAllString(sanitized, "")
+
+	if strings.Contains(sanitized, "script") {
+		nonCodingScriptTerms := []string{
+			"speaker script", "dialogue script", "movie script", "theatre script",
+			"theater script", "script writing", "script writer", "video script",
+			"audio script", "podcast script", "script for Kayla", "script for the",
+		}
+		hasNonCodingScript := false
+		for _, term := range nonCodingScriptTerms {
+			if strings.Contains(sanitized, strings.ToLower(term)) {
+				hasNonCodingScript = true
+				break
+			}
+		}
+		if hasNonCodingScript {
+			sanitized = strings.ReplaceAll(sanitized, "script", "")
+		}
+	}
+
+	return softwareDevRegex.MatchString(sanitized)
+}

internal/server/system.go

@@ -67,6 +67,7 @@ func (s *Server) handleGetSettings(c *gin.Context) {
 	providerCount := 0
 	modelCount := 0
 	s.registryMu.RLock()
+	defer s.registryMu.RUnlock()
 	if s.registry != nil {
 		providerCount = len(s.registry.Providers)
 		for _, p := range s.registry.Providers {

static/js/pages/monitoring.js

@@ -492,7 +492,7 @@ class MonitoringPage {
     simulateRequest() {
         const clients = ['client-1', 'client-2', 'client-3', 'client-4', 'client-5'];
         const providers = ['OpenAI', 'Gemini', 'DeepSeek', 'Grok'];
-        const models = ['gpt-4o', 'gpt-4o-mini', 'gemini-2.0-flash', 'deepseek-chat', 'grok-4-1-fast-non-reasoning'];
+        const models = ['gpt-4o', 'gpt-4o-mini', 'gemini-2.5-flash', 'deepseek-chat', 'grok-4-1-fast-non-reasoning'];
         const statuses = ['success', 'success', 'success', 'error', 'warning']; // Mostly success
         
         const request = {