feat: use model-aware prompt counting in Gemini paths

Preserve Gemini prompt token text during normalization and remove the hardcoded DeepSeek model from native Gemini usage helpers.

internal/httpapi/gemini/convert_request.go

@@ -36,16 +36,17 @@ func normalizeGeminiRequest(store ConfigReader, routeModel string, req map[strin
 	passThrough := collectGeminiPassThrough(req)
 
 	return promptcompat.StandardRequest{
-		Surface:        "google_gemini",
-		RequestedModel: requestedModel,
-		ResolvedModel:  resolvedModel,
-		ResponseModel:  requestedModel,
-		Messages:       messagesRaw,
-		FinalPrompt:    finalPrompt,
-		ToolNames:      toolNames,
-		Stream:         stream,
-		Thinking:       thinkingEnabled,
-		Search:         searchEnabled,
-		PassThrough:    passThrough,
+		Surface:         "google_gemini",
+		RequestedModel:  requestedModel,
+		ResolvedModel:   resolvedModel,
+		ResponseModel:   requestedModel,
+		Messages:        messagesRaw,
+		PromptTokenText: finalPrompt,
+		FinalPrompt:     finalPrompt,
+		ToolNames:       toolNames,
+		Stream:          stream,
+		Thinking:        thinkingEnabled,
+		Search:          searchEnabled,
+		PassThrough:     passThrough,
 	}, nil
 }

internal/httpapi/gemini/handler_generate.go

@@ -227,7 +227,7 @@ func (h *Handler) handleNonStreamGenerateContent(w http.ResponseWriter, resp *ht
 //nolint:unused // retained for native Gemini non-stream handling path.
 func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
 	parts := buildGeminiPartsFromFinal(finalText, finalThinking, toolNames)
-	usage := buildGeminiUsage(finalPrompt, finalThinking, finalText)
+	usage := buildGeminiUsage(model, finalPrompt, finalThinking, finalText)
 	return map[string]any{
 		"candidates": []map[string]any{
 			{
@@ -245,10 +245,10 @@ func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, final
 }
 
 //nolint:unused // retained for native Gemini non-stream handling path.
-func buildGeminiUsage(finalPrompt, finalThinking, finalText string) map[string]any {
-	promptTokens := util.EstimateTokens(finalPrompt)
-	reasoningTokens := util.EstimateTokens(finalThinking)
-	completionTokens := util.EstimateTokens(finalText)
+func buildGeminiUsage(model, finalPrompt, finalThinking, finalText string) map[string]any {
+	promptTokens := util.CountPromptTokens(finalPrompt, model)
+	reasoningTokens := util.CountOutputTokens(finalThinking, model)
+	completionTokens := util.CountOutputTokens(finalText, model)
 	return map[string]any{
 		"promptTokenCount":     promptTokens,
 		"candidatesTokenCount": reasoningTokens + completionTokens,

internal/httpapi/gemini/handler_stream_runtime.go

@@ -194,6 +194,6 @@ func (s *geminiStreamRuntime) finalize() {
 			},
 		},
 		"modelVersion":  s.model,
-		"usageMetadata": buildGeminiUsage(s.finalPrompt, finalThinking, finalText),
+		"usageMetadata": buildGeminiUsage(s.model, s.finalPrompt, finalThinking, finalText),
 	})
 }