chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-03 04:50:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed: #140 #133 #80

Browse Source 
feat(translator): add token counting functionality for Gemini, Claude, and CLI

- Introduced `TokenCount` handling across various Codex translators (Gemini, Claude, CLI) with respective implementations.
- Added utility methods for token counting and formatting responses.
- Integrated `tiktoken-go/tokenizer` library for tokenization.
- Updated CodexExecutor with token counting logic to support multiple models including GPT-5 variants.
- Refined go.mod and go.sum to include new dependencies.

feat(runtime): add token counting functionality across executors

- Implemented token counting in OpenAICompatExecutor, QwenExecutor, and IFlowExecutor.
- Added utilities for token counting and response formatting using `tiktoken-go/tokenizer`.
- Integrated token counting into translators for Gemini, Claude, and Gemini CLI.
- Enhanced multiple model support, including GPT-5 variants, for token counting.

docs: update environment variable instructions for multi-model support

- Added details for setting `ANTHROPIC_DEFAULT_OPUS_MODEL`, `ANTHROPIC_DEFAULT_SONNET_MODEL`, and `ANTHROPIC_DEFAULT_HAIKU_MODEL` for version 2.x.x.
- Clarified usage of `ANTHROPIC_MODEL` and `ANTHROPIC_SMALL_FAST_MODEL` for version 1.x.x.
- Expanded examples for setting environment variables across different models including Gemini, GPT-5, Claude, and Qwen3.
This commit is contained in:
Luis Pater
2025-10-26 04:51:23 +08:00
parent f6cf784cd1
commit a552a45b81
21 changed files with 588 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
internal/runtime/executor/qwen_executor.go
View File

@@ -207,7 +207,28 @@ func (e *QwenExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Aut
}
func (e *QwenExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
return cliproxyexecutor.Response{Payload: []byte{}}, fmt.Errorf("not implemented")
from := opts.SourceFormat
to := sdktranslator.FromString("openai")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
modelName := gjson.GetBytes(body, "model").String()
if strings.TrimSpace(modelName) == "" {
modelName = req.Model
}
enc, err := tokenizerForModel(modelName)
if err != nil {
return cliproxyexecutor.Response{}, fmt.Errorf("qwen executor: tokenizer init failed: %w", err)
}
count, err := countOpenAIChatTokens(enc, body)
if err != nil {
return cliproxyexecutor.Response{}, fmt.Errorf("qwen executor: token counting failed: %w", err)
}
usageJSON := buildOpenAIUsageJSON(count)
translated := sdktranslator.TranslateTokenCount(ctx, to, from, count, usageJSON)
return cliproxyexecutor.Response{Payload: []byte(translated)}, nil
}
func (e *QwenExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {