feat: add tokenizer-based token counting utilities

Use go-tiktoken with embedded vocabularies for accurate BPE token counting. CountPromptTokens applies conservative padding so returned context token counts stay slightly above the real value instead of undercounting.

go.mod

@@ -10,6 +10,11 @@ require (
 	github.com/router-for-me/CLIProxyAPI/v6 v6.9.14
 )
 
+require (
+	github.com/dlclark/regexp2 v1.11.5 // indirect
+	github.com/hupe1980/go-tiktoken v0.0.10 // indirect
+)
+
 require (
 	github.com/klauspost/compress v1.18.5 // indirect
 	github.com/sirupsen/logrus v1.9.4 // indirect

go.sum

@@ -2,10 +2,14 @@ github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eT
 github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
+github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/go-chi/chi/v5 v5.2.5 h1:Eg4myHZBjyvJmAFjFvWgrqDTXFyOzjj7YIm3L3mu6Ug=
 github.com/go-chi/chi/v5 v5.2.5/go.mod h1:X7Gx4mteadT3eDOMTsXzmI4/rwUpOwBHLpAfupzFJP0=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/hupe1980/go-tiktoken v0.0.10 h1:m6phOJaGyctqWdGIgwn9X8AfJvaG74tnQoDL+ntOUEQ=
+github.com/hupe1980/go-tiktoken v0.0.10/go.mod h1:NME6d8hrE+Jo+kLUZHhXShYV8e40hYkm4BbSLQKtvAo=
 github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE=
 github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=

internal/util/token_count.go

@@ -0,0 +1,87 @@
+package util
+
+import (
+	"strings"
+
+	tiktoken "github.com/hupe1980/go-tiktoken"
+)
+
+const (
+	defaultTokenizerModel = "gpt-4o"
+	claudeTokenizerModel  = "claude"
+)
+
+func CountPromptTokens(text, model string) int {
+	base := maxTokenCount(
+		EstimateTokens(text),
+		countWithTokenizer(text, model),
+	)
+	if base <= 0 {
+		return 0
+	}
+	return base + conservativePromptPadding(base)
+}
+
+func CountOutputTokens(text, model string) int {
+	base := maxTokenCount(
+		EstimateTokens(text),
+		countWithTokenizer(text, model),
+	)
+	if base <= 0 {
+		return 0
+	}
+	return base
+}
+
+func countWithTokenizer(text, model string) int {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return 0
+	}
+	encoding, err := tiktoken.NewEncodingForModel(tokenizerModelForCount(model))
+	if err != nil {
+		return 0
+	}
+	ids, _, err := encoding.Encode(text, nil, nil)
+	if err != nil {
+		return 0
+	}
+	return len(ids)
+}
+
+func tokenizerModelForCount(model string) string {
+	model = strings.ToLower(strings.TrimSpace(model))
+	if model == "" {
+		return defaultTokenizerModel
+	}
+	switch {
+	case strings.HasPrefix(model, "claude"):
+		return claudeTokenizerModel
+	case strings.HasPrefix(model, "gpt-4"), strings.HasPrefix(model, "gpt-5"), strings.HasPrefix(model, "o1"), strings.HasPrefix(model, "o3"), strings.HasPrefix(model, "o4"):
+		return defaultTokenizerModel
+	case strings.HasPrefix(model, "deepseek-v4"):
+		return defaultTokenizerModel
+	case strings.HasPrefix(model, "deepseek"):
+		return defaultTokenizerModel
+	default:
+		return defaultTokenizerModel
+	}
+}
+
+func conservativePromptPadding(base int) int {
+	padding := base / 50
+	if padding < 4 {
+		padding = 4
+	}
+	return padding
+}
+
+func maxTokenCount(values ...int) int {
+	best := 0
+	for _, v := range values {
+		if v > best {
+			best = v
+		}
+	}
+	return best
+}