debug: add max_tokens trace logging to chat completions handler

Logs what max_tokens the client sends, whether gophergate injects
one from the registry, and the final value forwarded to the provider.
Helps trace output truncation issues.

internal/server/server.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"log"
 	"net/http"
 	"strings"
 	"sync"
@@ -373,24 +374,35 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 		TopP:             req.TopP,
 		TopK:             req.TopK,
 		N:                req.N,
-		MaxTokens:        req.MaxTokens,
-		PresencePenalty:  req.PresencePenalty,
-		FrequencyPenalty: req.FrequencyPenalty,
-		Stream:           req.Stream != nil && *req.Stream,
-		Tools:            req.Tools,
-		ToolChoice:       req.ToolChoice,
-	}
+	MaxTokens:        req.MaxTokens,
+	PresencePenalty:  req.PresencePenalty,
+	FrequencyPenalty: req.FrequencyPenalty,
+	Stream:           req.Stream != nil && *req.Stream,
+	Tools:            req.Tools,
+	ToolChoice:       req.ToolChoice,
+}
 
-	// Inject max_tokens from model registry when client doesn't specify one.
-	// Prevents providers from applying a low default output cap.
-	if unifiedReq.MaxTokens == nil {
-		s.registryMu.RLock()
-		meta := s.registry.FindModel(modelID)
-		s.registryMu.RUnlock()
-		if meta != nil && meta.Limit != nil && meta.Limit.Output > 0 {
-			unifiedReq.MaxTokens = &meta.Limit.Output
-		}
+// Inject max_tokens from model registry when client doesn't specify one.
+// Prevents providers from applying a low default output cap.
+// DEBUG: Trace max_tokens through the proxy
+clientMaxTokens := "nil"
+if unifiedReq.MaxTokens != nil {
+	clientMaxTokens = fmt.Sprintf("%d", *unifiedReq.MaxTokens)
+}
+log.Printf("[DEBUG] %s: client max_tokens=%s", modelID, clientMaxTokens)
+if unifiedReq.MaxTokens == nil {
+	s.registryMu.RLock()
+	meta := s.registry.FindModel(modelID)
+	s.registryMu.RUnlock()
+	if meta != nil && meta.Limit != nil && meta.Limit.Output > 0 {
+		unifiedReq.MaxTokens = &meta.Limit.Output
+		log.Printf("[DEBUG] %s: injected registry max_tokens=%d", modelID, meta.Limit.Output)
+	} else {
+		log.Printf("[DEBUG] %s: no registry limit found, leaving max_tokens nil (provider default)", modelID)
 	}
+} else {
+	log.Printf("[DEBUG] %s: using client's max_tokens=%d", modelID, *unifiedReq.MaxTokens)
+}
 
 	// Handle Stop sequences
 	if req.Stop != nil {