Compare commits

..

54 Commits

Author SHA1 Message Date
Luis Pater
ee171bc563 feat(api): add ManagementTokenRequester interface for management token request endpoints 2025-12-29 02:42:29 +08:00
Luis Pater
457924828a Merge pull request #757 from ben-vargas/fix-thinking-toolchoice-conflict
Fix: disable thinking when tool_choice forces tool use
2025-12-28 14:04:30 +08:00
Ben Vargas
aca2ef6359 Fix: disable thinking when tool_choice forces tool use
Anthropic API does not allow extended thinking when tool_choice is set
to "any" or a specific tool. This was causing 400 errors when using
features like Amp's /handoff command which forces tool_choice.

Added disableThinkingIfToolChoiceForced() that removes thinking config
when incompatible tool_choice is detected, applied to both streaming
and non-streaming paths.

Fixes router-for-me/CLIProxyAPI#630
2025-12-27 16:31:37 -07:00
Luis Pater
ade7194792 feat(management): add generic API call handler to management endpoints 2025-12-28 04:40:32 +08:00
Luis Pater
3a436e116a feat(cliproxy): implement model aliasing and hashing for Codex configurations, enhance request routing logic, and normalize Codex model entries 2025-12-28 03:06:51 +08:00
Luis Pater
336867853b Merge pull request #756 from leaph/check-ai-thinking-settings
feat(iflow): add model-specific thinking configs for GLM-4.7 and Mini…
2025-12-28 02:08:27 +08:00
leaph
6403ff4ec4 feat(iflow): add model-specific thinking configs for GLM-4.7 and MiniMax-M2.1
- GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false}
- MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
- Added preserveReasoningContentInMessages() to support re-injection of reasoning
  content in assistant message history for multi-turn conversations
- Added ThinkingSupport to MiniMax-M2.1 model definition
2025-12-27 18:39:15 +01:00
Luis Pater
d222469b44 Update issue templates 2025-12-28 01:22:42 +08:00
Luis Pater
7646a2b877 Fixed: #749
fix(translators): ensure `gjson.String` content is non-empty before setting `parts` in OpenAI request logic
2025-12-28 00:54:26 +08:00
Luis Pater
62090f2568 Merge pull request #750 from router-for-me/config
fix(config): preserve original config structure and avoid default value pollution
2025-12-27 22:10:01 +08:00
Luis Pater
c281f4cbaf Fixed: #747
fix(translators): rename and integrate `usageMetadata` as `cpaUsageMetadata` in Claude processing logic
2025-12-27 22:02:11 +08:00
hkfires
09455f9e85 fix(config): make streaming keepalive and retries ints 2025-12-27 20:56:47 +08:00
hkfires
c8e72ba0dc fix(config): smart merge writes non-default new keys only 2025-12-27 20:28:54 +08:00
hkfires
375ef252ab docs(config): clarify merge mapping behavior 2025-12-27 19:30:21 +08:00
hkfires
ee552f8720 chore(config): update ignore patterns 2025-12-27 19:13:14 +08:00
hkfires
2e88c4858e fix(config): avoid adding new keys when merging 2025-12-27 19:00:47 +08:00
Luis Pater
3f50da85c1 Merge pull request #745 from router-for-me/auth
fix(auth): make provider rotation atomic
2025-12-27 13:01:22 +08:00
hkfires
8be06255f7 fix(auth): make provider rotation atomic 2025-12-27 12:56:48 +08:00
Luis Pater
72274099aa Fixed: #738
fix(translators): refine prompt token calculation by incorporating cached tokens in Claude response handling
2025-12-27 03:56:11 +08:00
Luis Pater
dcae098e23 Fixed: #736
fix(translators): handle gjson string types in Claude request processing to ensure consistent content parsing
2025-12-27 01:25:47 +08:00
Luis Pater
2eb05ec640 Merge pull request #727 from nguyenphutrong/main
docs: add Quotio to community projects
2025-12-26 11:53:09 +08:00
Luis Pater
3ce0d76aa4 feat(usage): add import/export functionality for usage statistics and enhance deduplication logic 2025-12-26 11:49:51 +08:00
Trong Nguyen
a00b79d9be docs(readme): add Quotio to community projects section 2025-12-26 10:46:05 +07:00
Luis Pater
33e53a2a56 fix(translators): ensure correct handling and output of multimodal assistant content across request handlers 2025-12-26 05:08:04 +08:00
Luis Pater
cd5b80785f Merge pull request #722 from hungthai1401/bugfix/remove-extra-args
Fixed incorrect function signature call to `NewBaseAPIHandlers`
2025-12-26 02:56:56 +08:00
Thai Nguyen Hung
54f71aa273 fix(test): remove extra argument from ExecuteStreamWithAuthManager call 2025-12-25 21:55:35 +07:00
Luis Pater
3f949b7f84 Merge pull request #704 from tinyc0der/add-index
fix(openai): add index field to image response for LiteLLM compatibility
2025-12-25 21:35:12 +08:00
Luis Pater
443c4538bb feat(config): add commercial-mode to optimize HTTP middleware for lower memory usage 2025-12-25 21:05:01 +08:00
TinyCoder
a7fc2ee4cf refactor(image): avoid using json.Marshal 2025-12-25 14:21:01 +07:00
Luis Pater
8e749ac22d docs(readme): update GLM model version from 4.6 to 4.7 in README and README_CN 2025-12-24 23:59:48 +08:00
Luis Pater
69e09d9bc7 docs(readme): update GLM model version from 4.6 to 4.7 in README and README_CN 2025-12-24 23:46:27 +08:00
Luis Pater
06ad527e8c Fixed: #696
fix(translators): adjust prompt token calculation by subtracting cached tokens across Gemini, OpenAI, and Claude handlers
2025-12-24 23:29:18 +08:00
Luis Pater
b7409dd2de Merge pull request #706 from router-for-me/log
Log
2025-12-24 22:24:39 +08:00
hkfires
5ba325a8fc refactor(logging): standardize request id formatting and layout 2025-12-24 22:03:07 +08:00
Luis Pater
d502840f91 Merge pull request #695 from NguyenSiTrung/main
feat: add cached token parsing for Gemini , Antigravity API responses
2025-12-24 21:58:55 +08:00
hkfires
99238a4b59 fix(logging): normalize warning level to warn 2025-12-24 21:11:37 +08:00
hkfires
6d43a2ff9a refactor(logging): inline request id in log output 2025-12-24 21:07:18 +08:00
Luis Pater
3faa1ca9af Merge pull request #700 from router-for-me/log
refactor(sdk/auth): rename manager.go to conductor.go
2025-12-24 19:36:24 +08:00
Luis Pater
9d975e0375 feat(models): add support for GLM-4.7 and MiniMax-M2.1 2025-12-24 19:30:57 +08:00
hkfires
2a6d8b78d4 feat(api): add endpoint to retrieve request logs by ID 2025-12-24 19:24:51 +08:00
TinyCoder
671558a822 fix(openai): add index field to image response for LiteLLM compatibility
LiteLLM's Pydantic model requires an index field in each image object.
Without it, responses fail validation with "images.0.index Field required".
2025-12-24 17:43:31 +07:00
hkfires
26fbb77901 refactor(sdk/auth): rename manager.go to conductor.go 2025-12-24 15:21:03 +08:00
NguyenSiTrung
a277302262 Merge remote-tracking branch 'upstream/main' 2025-12-24 10:54:09 +07:00
NguyenSiTrung
969c1a5b72 refactor: extract parseGeminiFamilyUsageDetail helper to reduce duplication 2025-12-24 10:22:31 +07:00
NguyenSiTrung
872339bceb feat: add cached token parsing for Gemini API responses 2025-12-24 10:20:11 +07:00
Luis Pater
5dc0dbc7aa Merge pull request #697 from Cubence-com/main
docs(readme): add Cubence sponsor and fix PackyCode link
2025-12-24 11:19:32 +08:00
Luis Pater
2b7ba54a2f Merge pull request #688 from router-for-me/feature/request-id-tracking
feat(logging): implement request ID tracking and propagation
2025-12-24 10:54:13 +08:00
hkfires
007c3304f2 feat(logging): scope request ID tracking to AI API endpoints 2025-12-24 09:17:09 +08:00
hkfires
e76ba0ede9 feat(logging): implement request ID tracking and propagation 2025-12-24 08:32:17 +08:00
Luis Pater
c06ac07e23 Merge pull request #686 from ajkdrag/main
feat: regex support for model-mappings
2025-12-24 04:37:44 +08:00
Fetters
8d25cf0d75 fix(readme): update PackyCode sponsorship link and remove redundant tbody 2025-12-23 23:44:40 +08:00
Fetters
64e85e7019 docs(readme): add Cubence sponsor 2025-12-23 23:30:57 +08:00
altamash
0c0aae1eac Robust change detection: replaced string concat with struct-based compare in hasModelMappingsChanged; removed boolTo01.
•  Performance: pre-allocate map and regex slice capacities in UpdateMappings.
   •  Verified with amp module tests (all passing)
2025-12-23 18:52:28 +05:30
altamash
5dcf7cb846 feat: regex support for model-mappings 2025-12-23 18:41:58 +05:30
49 changed files with 1886 additions and 280 deletions

View File

@@ -13,8 +13,6 @@ Dockerfile
docs/*
README.md
README_CN.md
MANAGEMENT_API.md
MANAGEMENT_API_CN.md
LICENSE
# Runtime data folders (should be mounted as volumes)
@@ -32,3 +30,4 @@ bin/*
.agent/*
.bmad/*
_bmad/*
_bmad-output/*

View File

@@ -7,6 +7,13 @@ assignees: ''
---
**Is it a request payload issue?**
[ ] Yes, this is a request payload issue. I am using a client/cURL to send a request payload, but I received an unexpected error.
[ ] No, it's another issue.
**If it's a request payload issue, you MUST know**
Our team doesn't have any GODs or ORACLEs or MIND READERs. Please make sure to attach the request log or curl payload.
**Describe the bug**
A clear and concise description of what the bug is.

7
.gitignore vendored
View File

@@ -11,11 +11,15 @@ bin/*
logs/*
conv/*
temp/*
refs/*
# Storage backends
pgstore/*
gitstore/*
objectstore/*
# Static assets
static/*
refs/*
# Authentication data
auths/*
@@ -35,6 +39,7 @@ GEMINI.md
.agent/*
.bmad/*
_bmad/*
_bmad-output/*
# macOS
.DS_Store

View File

@@ -10,11 +10,11 @@ So you can use local or multi-account CLI access with OpenAI(include Responses)/
## Sponsor
[![z.ai](https://assets.router-for.me/english.png)](https://z.ai/subscribe?ic=8JVLJQFSKB)
[![z.ai](https://assets.router-for.me/english-4.7.png)](https://z.ai/subscribe?ic=8JVLJQFSKB)
This project is sponsored by Z.ai, supporting us with their GLM CODING PLAN.
GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.6 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
GLM CODING PLAN is a subscription service designed for AI coding, starting at just $3/month. It provides access to their flagship GLM-4.7 model across 10+ popular AI coding tools (Claude Code, Cline, Roo Code, etc.), offering developers top-tier, fast, and stable coding experiences.
Get 10% OFF GLM CODING PLANhttps://z.ai/subscribe?ic=8JVLJQFSKB
@@ -26,6 +26,10 @@ Get 10% OFF GLM CODING PLANhttps://z.ai/subscribe?ic=8JVLJQFSKB
<td width="180"><a href="https://www.packyapi.com/register?aff=cliproxyapi"><img src="./assets/packycode.png" alt="PackyCode" width="150"></a></td>
<td>Thanks to PackyCode for sponsoring this project! PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. PackyCode provides special discounts for our software users: register using <a href="https://www.packyapi.com/register?aff=cliproxyapi">this link</a> and enter the "cliproxyapi" promo code during recharge to get 10% off.</td>
</tr>
<tr>
<td width="180"><a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa"><img src="./assets/cubence.png" alt="Cubence" width="150"></a></td>
<td>Thanks to Cubence for sponsoring this project! Cubence is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. Cubence provides special discounts for our software users: register using <a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa">this link</a> and enter the "CLIPROXYAPI" promo code during recharge to get 10% off.</td>
</tr>
</tbody>
</table>
@@ -110,6 +114,10 @@ CLI wrapper for instant switching between multiple Claude accounts and alternati
Native macOS GUI for managing CLIProxyAPI: configure providers, model mappings, and endpoints via OAuth - no API keys needed.
### [Quotio](https://github.com/nguyenphutrong/quotio)
Native macOS menu bar app that unifies Claude, Gemini, OpenAI, Qwen, and Antigravity subscriptions with real-time quota tracking and smart auto-failover for AI coding tools like Claude Code, OpenCode, and Droid - no API keys needed.
> [!NOTE]
> If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.

View File

@@ -10,11 +10,11 @@
## 赞助商
[![bigmodel.cn](https://assets.router-for.me/chinese.png)](https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII)
[![bigmodel.cn](https://assets.router-for.me/chinese-4.7.png)](https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII)
本项目由 Z智谱 提供赞助, 他们通过 GLM CODING PLAN 对本项目提供技术支持。
GLM CODING PLAN 是专为AI编码打造的订阅套餐每月最低仅需20元即可在十余款主流AI编码工具如 Claude Code、Cline、Roo Code 中畅享智谱旗舰模型GLM-4.6,为开发者提供顶尖的编码体验。
GLM CODING PLAN 是专为AI编码打造的订阅套餐每月最低仅需20元即可在十余款主流AI编码工具如 Claude Code、Cline、Roo Code 中畅享智谱旗舰模型GLM-4.7,为开发者提供顶尖的编码体验。
智谱AI为本软件提供了特别优惠使用以下链接购买可以享受九折优惠https://www.bigmodel.cn/claude-code?ic=RRVJPB5SII
@@ -26,9 +26,14 @@ GLM CODING PLAN 是专为AI编码打造的订阅套餐每月最低仅需20元
<td width="180"><a href="https://www.packyapi.com/register?aff=cliproxyapi"><img src="./assets/packycode.png" alt="PackyCode" width="150"></a></td>
<td>感谢 PackyCode 对本项目的赞助PackyCode 是一家可靠高效的 API 中转服务商,提供 Claude Code、Codex、Gemini 等多种服务的中转。PackyCode 为本软件用户提供了特别优惠:使用<a href="https://www.packyapi.com/register?aff=cliproxyapi">此链接</a>注册,并在充值时输入 "cliproxyapi" 优惠码即可享受九折优惠。</td>
</tr>
<tr>
<td width="180"><a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa"><img src="./assets/cubence.png" alt="Cubence" width="150"></a></td>
<td>感谢 Cubence 对本项目的赞助Cubence 是一家可靠高效的 API 中转服务商,提供 Claude Code、Codex、Gemini 等多种服务的中转。Cubence 为本软件用户提供了特别优惠:使用<a href="https://cubence.com/signup?code=CLIPROXYAPI&source=cpa">此链接</a>注册,并在充值时输入 "CLIPROXYAPI" 优惠码即可享受九折优惠。</td>
</tr>
</tbody>
</table>
## 功能特性
- 为 CLI 模型提供 OpenAI/Gemini/Claude/Codex 兼容的 API 端点
@@ -108,6 +113,10 @@ CLI 封装器,用于通过 CLIProxyAPI OAuth 即时切换多个 Claude 账户
基于 macOS 平台的原生 CLIProxyAPI GUI配置供应商、模型映射以及OAuth端点无需 API 密钥。
### [Quotio](https://github.com/nguyenphutrong/quotio)
原生 macOS 菜单栏应用,统一管理 Claude、Gemini、OpenAI、Qwen 和 Antigravity 订阅,提供实时配额追踪和智能自动故障转移,支持 Claude Code、OpenCode 和 Droid 等 AI 编程工具,无需 API 密钥。
> [!NOTE]
> 如果你开发了基于 CLIProxyAPI 的项目,请提交一个 PR拉取请求将其添加到此列表中。

BIN
assets/cubence.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 51 KiB

View File

@@ -39,6 +39,9 @@ api-keys:
# Enable debug logging
debug: false
# When true, disable high-overhead HTTP middleware features to reduce per-request memory usage under high concurrency.
commercial-mode: false
# When true, write application logs to rotating files instead of stdout
logging-to-file: false
@@ -101,6 +104,9 @@ ws-auth: false
# headers:
# X-Custom-Header: "custom-value"
# proxy-url: "socks5://proxy.example.com:1080" # optional: per-key proxy override
# models:
# - name: "gpt-5-codex" # upstream model name
# alias: "codex-latest" # client alias mapped to the upstream model
# excluded-models:
# - "gpt-5.1" # exclude specific models (exact match)
# - "gpt-5-*" # wildcard matching prefix (e.g. gpt-5-medium, gpt-5-codex)

View File

@@ -0,0 +1,538 @@
package management
import (
"context"
"encoding/json"
"fmt"
"io"
"net"
"net/http"
"net/url"
"strings"
"time"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/runtime/geminicli"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
log "github.com/sirupsen/logrus"
"golang.org/x/net/proxy"
"golang.org/x/oauth2"
"golang.org/x/oauth2/google"
)
const defaultAPICallTimeout = 60 * time.Second
const (
geminiOAuthClientID = "681255809395-oo8ft2oprdrnp9e3aqf6av3hmdib135j.apps.googleusercontent.com"
geminiOAuthClientSecret = "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"
)
var geminiOAuthScopes = []string{
"https://www.googleapis.com/auth/cloud-platform",
"https://www.googleapis.com/auth/userinfo.email",
"https://www.googleapis.com/auth/userinfo.profile",
}
type apiCallRequest struct {
AuthIndexSnake *string `json:"auth_index"`
AuthIndexCamel *string `json:"authIndex"`
AuthIndexPascal *string `json:"AuthIndex"`
Method string `json:"method"`
URL string `json:"url"`
Header map[string]string `json:"header"`
Data string `json:"data"`
}
type apiCallResponse struct {
StatusCode int `json:"status_code"`
Header map[string][]string `json:"header"`
Body string `json:"body"`
}
// APICall makes a generic HTTP request on behalf of the management API caller.
// It is protected by the management middleware.
//
// Endpoint:
//
// POST /v0/management/api-call
//
// Authentication:
//
// Same as other management APIs (requires a management key and remote-management rules).
// You can provide the key via:
// - Authorization: Bearer <key>
// - X-Management-Key: <key>
//
// Request JSON:
// - auth_index / authIndex / AuthIndex (optional):
// The credential "auth_index" from GET /v0/management/auth-files (or other endpoints returning it).
// If omitted or not found, credential-specific proxy/token substitution is skipped.
// - method (required): HTTP method, e.g. GET, POST, PUT, PATCH, DELETE.
// - url (required): Absolute URL including scheme and host, e.g. "https://api.example.com/v1/ping".
// - header (optional): Request headers map.
// Supports magic variable "$TOKEN$" which is replaced using the selected credential:
// 1) metadata.access_token
// 2) attributes.api_key
// 3) metadata.token / metadata.id_token / metadata.cookie
// Example: {"Authorization":"Bearer $TOKEN$"}.
// Note: if you need to override the HTTP Host header, set header["Host"].
// - data (optional): Raw request body as string (useful for POST/PUT/PATCH).
//
// Proxy selection (highest priority first):
// 1. Selected credential proxy_url
// 2. Global config proxy-url
// 3. Direct connect (environment proxies are not used)
//
// Response JSON (returned with HTTP 200 when the APICall itself succeeds):
// - status_code: Upstream HTTP status code.
// - header: Upstream response headers.
// - body: Upstream response body as string.
//
// Example:
//
// curl -sS -X POST "http://127.0.0.1:8317/v0/management/api-call" \
// -H "Authorization: Bearer <MANAGEMENT_KEY>" \
// -H "Content-Type: application/json" \
// -d '{"auth_index":"<AUTH_INDEX>","method":"GET","url":"https://api.example.com/v1/ping","header":{"Authorization":"Bearer $TOKEN$"}}'
//
// curl -sS -X POST "http://127.0.0.1:8317/v0/management/api-call" \
// -H "Authorization: Bearer 831227" \
// -H "Content-Type: application/json" \
// -d '{"auth_index":"<AUTH_INDEX>","method":"POST","url":"https://api.example.com/v1/fetchAvailableModels","header":{"Authorization":"Bearer $TOKEN$","Content-Type":"application/json","User-Agent":"cliproxyapi"},"data":"{}"}'
func (h *Handler) APICall(c *gin.Context) {
var body apiCallRequest
if errBindJSON := c.ShouldBindJSON(&body); errBindJSON != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid body"})
return
}
method := strings.ToUpper(strings.TrimSpace(body.Method))
if method == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing method"})
return
}
urlStr := strings.TrimSpace(body.URL)
if urlStr == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing url"})
return
}
parsedURL, errParseURL := url.Parse(urlStr)
if errParseURL != nil || parsedURL.Scheme == "" || parsedURL.Host == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid url"})
return
}
authIndex := firstNonEmptyString(body.AuthIndexSnake, body.AuthIndexCamel, body.AuthIndexPascal)
auth := h.authByIndex(authIndex)
reqHeaders := body.Header
if reqHeaders == nil {
reqHeaders = map[string]string{}
}
var hostOverride string
var token string
var tokenResolved bool
var tokenErr error
for key, value := range reqHeaders {
if !strings.Contains(value, "$TOKEN$") {
continue
}
if !tokenResolved {
token, tokenErr = h.resolveTokenForAuth(c.Request.Context(), auth)
tokenResolved = true
}
if auth != nil && token == "" {
if tokenErr != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "auth token refresh failed"})
return
}
c.JSON(http.StatusBadRequest, gin.H{"error": "auth token not found"})
return
}
if token == "" {
continue
}
reqHeaders[key] = strings.ReplaceAll(value, "$TOKEN$", token)
}
var requestBody io.Reader
if body.Data != "" {
requestBody = strings.NewReader(body.Data)
}
req, errNewRequest := http.NewRequestWithContext(c.Request.Context(), method, urlStr, requestBody)
if errNewRequest != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "failed to build request"})
return
}
for key, value := range reqHeaders {
if strings.EqualFold(key, "host") {
hostOverride = strings.TrimSpace(value)
continue
}
req.Header.Set(key, value)
}
if hostOverride != "" {
req.Host = hostOverride
}
httpClient := &http.Client{
Timeout: defaultAPICallTimeout,
}
httpClient.Transport = h.apiCallTransport(auth)
resp, errDo := httpClient.Do(req)
if errDo != nil {
log.WithError(errDo).Debug("management APICall request failed")
c.JSON(http.StatusBadGateway, gin.H{"error": "request failed"})
return
}
defer func() {
if errClose := resp.Body.Close(); errClose != nil {
log.Errorf("response body close error: %v", errClose)
}
}()
respBody, errReadAll := io.ReadAll(resp.Body)
if errReadAll != nil {
c.JSON(http.StatusBadGateway, gin.H{"error": "failed to read response"})
return
}
c.JSON(http.StatusOK, apiCallResponse{
StatusCode: resp.StatusCode,
Header: resp.Header,
Body: string(respBody),
})
}
func firstNonEmptyString(values ...*string) string {
for _, v := range values {
if v == nil {
continue
}
if out := strings.TrimSpace(*v); out != "" {
return out
}
}
return ""
}
func tokenValueForAuth(auth *coreauth.Auth) string {
if auth == nil {
return ""
}
if v := tokenValueFromMetadata(auth.Metadata); v != "" {
return v
}
if auth.Attributes != nil {
if v := strings.TrimSpace(auth.Attributes["api_key"]); v != "" {
return v
}
}
if shared := geminicli.ResolveSharedCredential(auth.Runtime); shared != nil {
if v := tokenValueFromMetadata(shared.MetadataSnapshot()); v != "" {
return v
}
}
return ""
}
func (h *Handler) resolveTokenForAuth(ctx context.Context, auth *coreauth.Auth) (string, error) {
if auth == nil {
return "", nil
}
provider := strings.ToLower(strings.TrimSpace(auth.Provider))
if provider == "gemini-cli" {
token, errToken := h.refreshGeminiOAuthAccessToken(ctx, auth)
return token, errToken
}
return tokenValueForAuth(auth), nil
}
func (h *Handler) refreshGeminiOAuthAccessToken(ctx context.Context, auth *coreauth.Auth) (string, error) {
if ctx == nil {
ctx = context.Background()
}
if auth == nil {
return "", nil
}
metadata, updater := geminiOAuthMetadata(auth)
if len(metadata) == 0 {
return "", fmt.Errorf("gemini oauth metadata missing")
}
base := make(map[string]any)
if tokenRaw, ok := metadata["token"].(map[string]any); ok && tokenRaw != nil {
base = cloneMap(tokenRaw)
}
var token oauth2.Token
if len(base) > 0 {
if raw, errMarshal := json.Marshal(base); errMarshal == nil {
_ = json.Unmarshal(raw, &token)
}
}
if token.AccessToken == "" {
token.AccessToken = stringValue(metadata, "access_token")
}
if token.RefreshToken == "" {
token.RefreshToken = stringValue(metadata, "refresh_token")
}
if token.TokenType == "" {
token.TokenType = stringValue(metadata, "token_type")
}
if token.Expiry.IsZero() {
if expiry := stringValue(metadata, "expiry"); expiry != "" {
if ts, errParseTime := time.Parse(time.RFC3339, expiry); errParseTime == nil {
token.Expiry = ts
}
}
}
conf := &oauth2.Config{
ClientID: geminiOAuthClientID,
ClientSecret: geminiOAuthClientSecret,
Scopes: geminiOAuthScopes,
Endpoint: google.Endpoint,
}
ctxToken := ctx
httpClient := &http.Client{
Timeout: defaultAPICallTimeout,
Transport: h.apiCallTransport(auth),
}
ctxToken = context.WithValue(ctxToken, oauth2.HTTPClient, httpClient)
src := conf.TokenSource(ctxToken, &token)
currentToken, errToken := src.Token()
if errToken != nil {
return "", errToken
}
merged := buildOAuthTokenMap(base, currentToken)
fields := buildOAuthTokenFields(currentToken, merged)
if updater != nil {
updater(fields)
}
return strings.TrimSpace(currentToken.AccessToken), nil
}
func geminiOAuthMetadata(auth *coreauth.Auth) (map[string]any, func(map[string]any)) {
if auth == nil {
return nil, nil
}
if shared := geminicli.ResolveSharedCredential(auth.Runtime); shared != nil {
snapshot := shared.MetadataSnapshot()
return snapshot, func(fields map[string]any) { shared.MergeMetadata(fields) }
}
return auth.Metadata, func(fields map[string]any) {
if auth.Metadata == nil {
auth.Metadata = make(map[string]any)
}
for k, v := range fields {
auth.Metadata[k] = v
}
}
}
func stringValue(metadata map[string]any, key string) string {
if len(metadata) == 0 || key == "" {
return ""
}
if v, ok := metadata[key].(string); ok {
return strings.TrimSpace(v)
}
return ""
}
func cloneMap(in map[string]any) map[string]any {
if len(in) == 0 {
return nil
}
out := make(map[string]any, len(in))
for k, v := range in {
out[k] = v
}
return out
}
func buildOAuthTokenMap(base map[string]any, tok *oauth2.Token) map[string]any {
merged := cloneMap(base)
if merged == nil {
merged = make(map[string]any)
}
if tok == nil {
return merged
}
if raw, errMarshal := json.Marshal(tok); errMarshal == nil {
var tokenMap map[string]any
if errUnmarshal := json.Unmarshal(raw, &tokenMap); errUnmarshal == nil {
for k, v := range tokenMap {
merged[k] = v
}
}
}
return merged
}
func buildOAuthTokenFields(tok *oauth2.Token, merged map[string]any) map[string]any {
fields := make(map[string]any, 5)
if tok != nil && tok.AccessToken != "" {
fields["access_token"] = tok.AccessToken
}
if tok != nil && tok.TokenType != "" {
fields["token_type"] = tok.TokenType
}
if tok != nil && tok.RefreshToken != "" {
fields["refresh_token"] = tok.RefreshToken
}
if tok != nil && !tok.Expiry.IsZero() {
fields["expiry"] = tok.Expiry.Format(time.RFC3339)
}
if len(merged) > 0 {
fields["token"] = cloneMap(merged)
}
return fields
}
func tokenValueFromMetadata(metadata map[string]any) string {
if len(metadata) == 0 {
return ""
}
if v, ok := metadata["accessToken"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
if v, ok := metadata["access_token"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
if tokenRaw, ok := metadata["token"]; ok && tokenRaw != nil {
switch typed := tokenRaw.(type) {
case string:
if v := strings.TrimSpace(typed); v != "" {
return v
}
case map[string]any:
if v, ok := typed["access_token"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
if v, ok := typed["accessToken"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
case map[string]string:
if v := strings.TrimSpace(typed["access_token"]); v != "" {
return v
}
if v := strings.TrimSpace(typed["accessToken"]); v != "" {
return v
}
}
}
if v, ok := metadata["token"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
if v, ok := metadata["id_token"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
if v, ok := metadata["cookie"].(string); ok && strings.TrimSpace(v) != "" {
return strings.TrimSpace(v)
}
return ""
}
func (h *Handler) authByIndex(authIndex string) *coreauth.Auth {
authIndex = strings.TrimSpace(authIndex)
if authIndex == "" || h == nil || h.authManager == nil {
return nil
}
auths := h.authManager.List()
for _, auth := range auths {
if auth == nil {
continue
}
auth.EnsureIndex()
if auth.Index == authIndex {
return auth
}
}
return nil
}
func (h *Handler) apiCallTransport(auth *coreauth.Auth) http.RoundTripper {
var proxyCandidates []string
if auth != nil {
if proxyStr := strings.TrimSpace(auth.ProxyURL); proxyStr != "" {
proxyCandidates = append(proxyCandidates, proxyStr)
}
}
if h != nil && h.cfg != nil {
if proxyStr := strings.TrimSpace(h.cfg.ProxyURL); proxyStr != "" {
proxyCandidates = append(proxyCandidates, proxyStr)
}
}
for _, proxyStr := range proxyCandidates {
if transport := buildProxyTransport(proxyStr); transport != nil {
return transport
}
}
transport, ok := http.DefaultTransport.(*http.Transport)
if !ok || transport == nil {
return &http.Transport{Proxy: nil}
}
clone := transport.Clone()
clone.Proxy = nil
return clone
}
func buildProxyTransport(proxyStr string) *http.Transport {
proxyStr = strings.TrimSpace(proxyStr)
if proxyStr == "" {
return nil
}
proxyURL, errParse := url.Parse(proxyStr)
if errParse != nil {
log.WithError(errParse).Debug("parse proxy URL failed")
return nil
}
if proxyURL.Scheme == "" || proxyURL.Host == "" {
log.Debug("proxy URL missing scheme/host")
return nil
}
if proxyURL.Scheme == "socks5" {
var proxyAuth *proxy.Auth
if proxyURL.User != nil {
username := proxyURL.User.Username()
password, _ := proxyURL.User.Password()
proxyAuth = &proxy.Auth{User: username, Password: password}
}
dialer, errSOCKS5 := proxy.SOCKS5("tcp", proxyURL.Host, proxyAuth, proxy.Direct)
if errSOCKS5 != nil {
log.WithError(errSOCKS5).Debug("create SOCKS5 dialer failed")
return nil
}
return &http.Transport{
Proxy: nil,
DialContext: func(ctx context.Context, network, addr string) (net.Conn, error) {
return dialer.Dial(network, addr)
},
}
}
if proxyURL.Scheme == "http" || proxyURL.Scheme == "https" {
return &http.Transport{Proxy: http.ProxyURL(proxyURL)}
}
log.Debugf("unsupported proxy scheme: %s", proxyURL.Scheme)
return nil
}

View File

@@ -597,11 +597,7 @@ func (h *Handler) PutCodexKeys(c *gin.Context) {
filtered := make([]config.CodexKey, 0, len(arr))
for i := range arr {
entry := arr[i]
entry.APIKey = strings.TrimSpace(entry.APIKey)
entry.BaseURL = strings.TrimSpace(entry.BaseURL)
entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
entry.Headers = config.NormalizeHeaders(entry.Headers)
entry.ExcludedModels = config.NormalizeExcludedModels(entry.ExcludedModels)
normalizeCodexKey(&entry)
if entry.BaseURL == "" {
continue
}
@@ -613,12 +609,13 @@ func (h *Handler) PutCodexKeys(c *gin.Context) {
}
func (h *Handler) PatchCodexKey(c *gin.Context) {
type codexKeyPatch struct {
APIKey *string `json:"api-key"`
Prefix *string `json:"prefix"`
BaseURL *string `json:"base-url"`
ProxyURL *string `json:"proxy-url"`
Headers *map[string]string `json:"headers"`
ExcludedModels *[]string `json:"excluded-models"`
APIKey *string `json:"api-key"`
Prefix *string `json:"prefix"`
BaseURL *string `json:"base-url"`
ProxyURL *string `json:"proxy-url"`
Models *[]config.CodexModel `json:"models"`
Headers *map[string]string `json:"headers"`
ExcludedModels *[]string `json:"excluded-models"`
}
var body struct {
Index *int `json:"index"`
@@ -667,12 +664,16 @@ func (h *Handler) PatchCodexKey(c *gin.Context) {
if body.Value.ProxyURL != nil {
entry.ProxyURL = strings.TrimSpace(*body.Value.ProxyURL)
}
if body.Value.Models != nil {
entry.Models = append([]config.CodexModel(nil), (*body.Value.Models)...)
}
if body.Value.Headers != nil {
entry.Headers = config.NormalizeHeaders(*body.Value.Headers)
}
if body.Value.ExcludedModels != nil {
entry.ExcludedModels = config.NormalizeExcludedModels(*body.Value.ExcludedModels)
}
normalizeCodexKey(&entry)
h.cfg.CodexKey[targetIndex] = entry
h.cfg.SanitizeCodexKeys()
h.persist(c)
@@ -762,6 +763,32 @@ func normalizeClaudeKey(entry *config.ClaudeKey) {
entry.Models = normalized
}
func normalizeCodexKey(entry *config.CodexKey) {
if entry == nil {
return
}
entry.APIKey = strings.TrimSpace(entry.APIKey)
entry.Prefix = strings.TrimSpace(entry.Prefix)
entry.BaseURL = strings.TrimSpace(entry.BaseURL)
entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
entry.Headers = config.NormalizeHeaders(entry.Headers)
entry.ExcludedModels = config.NormalizeExcludedModels(entry.ExcludedModels)
if len(entry.Models) == 0 {
return
}
normalized := make([]config.CodexModel, 0, len(entry.Models))
for i := range entry.Models {
model := entry.Models[i]
model.Name = strings.TrimSpace(model.Name)
model.Alias = strings.TrimSpace(model.Alias)
if model.Name == "" && model.Alias == "" {
continue
}
normalized = append(normalized, model)
}
entry.Models = normalized
}
// GetAmpCode returns the complete ampcode configuration.
func (h *Handler) GetAmpCode(c *gin.Context) {
if h == nil || h.cfg == nil {

View File

@@ -59,6 +59,11 @@ func NewHandler(cfg *config.Config, configFilePath string, manager *coreauth.Man
}
}
// NewHandler creates a new management handler instance.
func NewHandlerWithoutConfigFilePath(cfg *config.Config, manager *coreauth.Manager) *Handler {
return NewHandler(cfg, "", manager)
}
// SetConfig updates the in-memory config reference when the server hot-reloads.
func (h *Handler) SetConfig(cfg *config.Config) { h.cfg = cfg }

View File

@@ -209,6 +209,94 @@ func (h *Handler) GetRequestErrorLogs(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"files": files})
}
// GetRequestLogByID finds and downloads a request log file by its request ID.
// The ID is matched against the suffix of log file names (format: *-{requestID}.log).
func (h *Handler) GetRequestLogByID(c *gin.Context) {
if h == nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "handler unavailable"})
return
}
if h.cfg == nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": "configuration unavailable"})
return
}
dir := h.logDirectory()
if strings.TrimSpace(dir) == "" {
c.JSON(http.StatusInternalServerError, gin.H{"error": "log directory not configured"})
return
}
requestID := strings.TrimSpace(c.Param("id"))
if requestID == "" {
requestID = strings.TrimSpace(c.Query("id"))
}
if requestID == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "missing request ID"})
return
}
if strings.ContainsAny(requestID, "/\\") {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid request ID"})
return
}
entries, err := os.ReadDir(dir)
if err != nil {
if os.IsNotExist(err) {
c.JSON(http.StatusNotFound, gin.H{"error": "log directory not found"})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to list log directory: %v", err)})
return
}
suffix := "-" + requestID + ".log"
var matchedFile string
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
if strings.HasSuffix(name, suffix) {
matchedFile = name
break
}
}
if matchedFile == "" {
c.JSON(http.StatusNotFound, gin.H{"error": "log file not found for the given request ID"})
return
}
dirAbs, errAbs := filepath.Abs(dir)
if errAbs != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to resolve log directory: %v", errAbs)})
return
}
fullPath := filepath.Clean(filepath.Join(dirAbs, matchedFile))
prefix := dirAbs + string(os.PathSeparator)
if !strings.HasPrefix(fullPath, prefix) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file path"})
return
}
info, errStat := os.Stat(fullPath)
if errStat != nil {
if os.IsNotExist(errStat) {
c.JSON(http.StatusNotFound, gin.H{"error": "log file not found"})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to read log file: %v", errStat)})
return
}
if info.IsDir() {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid log file"})
return
}
c.FileAttachment(fullPath, matchedFile)
}
// DownloadRequestErrorLog downloads a specific error request log file by name.
func (h *Handler) DownloadRequestErrorLog(c *gin.Context) {
if h == nil {

View File

@@ -1,12 +1,25 @@
package management
import (
"encoding/json"
"net/http"
"time"
"github.com/gin-gonic/gin"
"github.com/router-for-me/CLIProxyAPI/v6/internal/usage"
)
type usageExportPayload struct {
Version int `json:"version"`
ExportedAt time.Time `json:"exported_at"`
Usage usage.StatisticsSnapshot `json:"usage"`
}
type usageImportPayload struct {
Version int `json:"version"`
Usage usage.StatisticsSnapshot `json:"usage"`
}
// GetUsageStatistics returns the in-memory request statistics snapshot.
func (h *Handler) GetUsageStatistics(c *gin.Context) {
var snapshot usage.StatisticsSnapshot
@@ -18,3 +31,49 @@ func (h *Handler) GetUsageStatistics(c *gin.Context) {
"failed_requests": snapshot.FailureCount,
})
}
// ExportUsageStatistics returns a complete usage snapshot for backup/migration.
func (h *Handler) ExportUsageStatistics(c *gin.Context) {
var snapshot usage.StatisticsSnapshot
if h != nil && h.usageStats != nil {
snapshot = h.usageStats.Snapshot()
}
c.JSON(http.StatusOK, usageExportPayload{
Version: 1,
ExportedAt: time.Now().UTC(),
Usage: snapshot,
})
}
// ImportUsageStatistics merges a previously exported usage snapshot into memory.
func (h *Handler) ImportUsageStatistics(c *gin.Context) {
if h == nil || h.usageStats == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "usage statistics unavailable"})
return
}
data, err := c.GetRawData()
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "failed to read request body"})
return
}
var payload usageImportPayload
if err := json.Unmarshal(data, &payload); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid json"})
return
}
if payload.Version != 0 && payload.Version != 1 {
c.JSON(http.StatusBadRequest, gin.H{"error": "unsupported version"})
return
}
result := h.usageStats.MergeSnapshot(payload.Usage)
snapshot := h.usageStats.Snapshot()
c.JSON(http.StatusOK, gin.H{
"added": result.Added,
"skipped": result.Skipped,
"total_requests": snapshot.TotalRequests,
"failed_requests": snapshot.FailureCount,
})
}

View File

@@ -98,10 +98,11 @@ func captureRequestInfo(c *gin.Context) (*RequestInfo, error) {
}
return &RequestInfo{
URL: url,
Method: method,
Headers: headers,
Body: body,
URL: url,
Method: method,
Headers: headers,
Body: body,
RequestID: logging.GetGinRequestID(c),
}, nil
}

View File

@@ -15,10 +15,11 @@ import (
// RequestInfo holds essential details of an incoming HTTP request for logging purposes.
type RequestInfo struct {
URL string // URL is the request URL.
Method string // Method is the HTTP method (e.g., GET, POST).
Headers map[string][]string // Headers contains the request headers.
Body []byte // Body is the raw request body.
URL string // URL is the request URL.
Method string // Method is the HTTP method (e.g., GET, POST).
Headers map[string][]string // Headers contains the request headers.
Body []byte // Body is the raw request body.
RequestID string // RequestID is the unique identifier for the request.
}
// ResponseWriterWrapper wraps the standard gin.ResponseWriter to intercept and log response data.
@@ -149,6 +150,7 @@ func (w *ResponseWriterWrapper) WriteHeader(statusCode int) {
w.requestInfo.Method,
w.requestInfo.Headers,
w.requestInfo.Body,
w.requestInfo.RequestID,
)
if err == nil {
w.streamWriter = streamWriter
@@ -346,7 +348,7 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
}
if loggerWithOptions, ok := w.logger.(interface {
LogRequestWithOptions(string, string, map[string][]string, []byte, int, map[string][]string, []byte, []byte, []byte, []*interfaces.ErrorMessage, bool) error
LogRequestWithOptions(string, string, map[string][]string, []byte, int, map[string][]string, []byte, []byte, []byte, []*interfaces.ErrorMessage, bool, string) error
}); ok {
return loggerWithOptions.LogRequestWithOptions(
w.requestInfo.URL,
@@ -360,6 +362,7 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
apiResponseBody,
apiResponseErrors,
forceLog,
w.requestInfo.RequestID,
)
}
@@ -374,5 +377,6 @@ func (w *ResponseWriterWrapper) logRequest(statusCode int, headers map[string][]
apiRequestBody,
apiResponseBody,
apiResponseErrors,
w.requestInfo.RequestID,
)
}

View File

@@ -279,16 +279,23 @@ func (m *AmpModule) hasModelMappingsChanged(old *config.AmpCode, new *config.Amp
return true
}
// Build map for efficient comparison
oldMap := make(map[string]string, len(old.ModelMappings))
// Build map for efficient and robust comparison
type mappingInfo struct {
to string
regex bool
}
oldMap := make(map[string]mappingInfo, len(old.ModelMappings))
for _, mapping := range old.ModelMappings {
oldMap[strings.TrimSpace(mapping.From)] = strings.TrimSpace(mapping.To)
oldMap[strings.TrimSpace(mapping.From)] = mappingInfo{
to: strings.TrimSpace(mapping.To),
regex: mapping.Regex,
}
}
for _, mapping := range new.ModelMappings {
from := strings.TrimSpace(mapping.From)
to := strings.TrimSpace(mapping.To)
if oldTo, exists := oldMap[from]; !exists || oldTo != to {
if oldVal, exists := oldMap[from]; !exists || oldVal.to != to || oldVal.regex != mapping.Regex {
return true
}
}

View File

@@ -3,6 +3,7 @@
package amp
import (
"regexp"
"strings"
"sync"
@@ -26,13 +27,15 @@ type ModelMapper interface {
// DefaultModelMapper implements ModelMapper with thread-safe mapping storage.
type DefaultModelMapper struct {
mu sync.RWMutex
mappings map[string]string // from -> to (normalized lowercase keys)
mappings map[string]string // exact: from -> to (normalized lowercase keys)
regexps []regexMapping // regex rules evaluated in order
}
// NewModelMapper creates a new model mapper with the given initial mappings.
func NewModelMapper(mappings []config.AmpModelMapping) *DefaultModelMapper {
m := &DefaultModelMapper{
mappings: make(map[string]string),
regexps: nil,
}
m.UpdateMappings(mappings)
return m
@@ -55,7 +58,18 @@ func (m *DefaultModelMapper) MapModel(requestedModel string) string {
// Check for direct mapping
targetModel, exists := m.mappings[normalizedRequest]
if !exists {
return ""
// Try regex mappings in order
base, _ := util.NormalizeThinkingModel(requestedModel)
for _, rm := range m.regexps {
if rm.re.MatchString(requestedModel) || (base != "" && rm.re.MatchString(base)) {
targetModel = rm.to
exists = true
break
}
}
if !exists {
return ""
}
}
// Verify target model has available providers
@@ -78,6 +92,7 @@ func (m *DefaultModelMapper) UpdateMappings(mappings []config.AmpModelMapping) {
// Clear and rebuild mappings
m.mappings = make(map[string]string, len(mappings))
m.regexps = make([]regexMapping, 0, len(mappings))
for _, mapping := range mappings {
from := strings.TrimSpace(mapping.From)
@@ -88,16 +103,30 @@ func (m *DefaultModelMapper) UpdateMappings(mappings []config.AmpModelMapping) {
continue
}
// Store with normalized lowercase key for case-insensitive lookup
normalizedFrom := strings.ToLower(from)
m.mappings[normalizedFrom] = to
log.Debugf("amp model mapping registered: %s -> %s", from, to)
if mapping.Regex {
// Compile case-insensitive regex; wrap with (?i) to match behavior of exact lookups
pattern := "(?i)" + from
re, err := regexp.Compile(pattern)
if err != nil {
log.Warnf("amp model mapping: invalid regex %q: %v", from, err)
continue
}
m.regexps = append(m.regexps, regexMapping{re: re, to: to})
log.Debugf("amp model regex mapping registered: /%s/ -> %s", from, to)
} else {
// Store with normalized lowercase key for case-insensitive lookup
normalizedFrom := strings.ToLower(from)
m.mappings[normalizedFrom] = to
log.Debugf("amp model mapping registered: %s -> %s", from, to)
}
}
if len(m.mappings) > 0 {
log.Infof("amp model mapping: loaded %d mapping(s)", len(m.mappings))
}
if n := len(m.regexps); n > 0 {
log.Infof("amp model mapping: loaded %d regex mapping(s)", n)
}
}
// GetMappings returns a copy of current mappings (for debugging/status).
@@ -111,3 +140,8 @@ func (m *DefaultModelMapper) GetMappings() map[string]string {
}
return result
}
type regexMapping struct {
re *regexp.Regexp
to string
}

View File

@@ -203,3 +203,81 @@ func TestModelMapper_GetMappings_ReturnsCopy(t *testing.T) {
t.Error("Original map was modified")
}
}
func TestModelMapper_Regex_MatchBaseWithoutParens(t *testing.T) {
reg := registry.GetGlobalRegistry()
reg.RegisterClient("test-client-regex-1", "gemini", []*registry.ModelInfo{
{ID: "gemini-2.5-pro", OwnedBy: "google", Type: "gemini"},
})
defer reg.UnregisterClient("test-client-regex-1")
mappings := []config.AmpModelMapping{
{From: "^gpt-5$", To: "gemini-2.5-pro", Regex: true},
}
mapper := NewModelMapper(mappings)
// Incoming model has reasoning suffix but should match base via regex
result := mapper.MapModel("gpt-5(high)")
if result != "gemini-2.5-pro" {
t.Errorf("Expected gemini-2.5-pro, got %s", result)
}
}
func TestModelMapper_Regex_ExactPrecedence(t *testing.T) {
reg := registry.GetGlobalRegistry()
reg.RegisterClient("test-client-regex-2", "claude", []*registry.ModelInfo{
{ID: "claude-sonnet-4", OwnedBy: "anthropic", Type: "claude"},
})
reg.RegisterClient("test-client-regex-3", "gemini", []*registry.ModelInfo{
{ID: "gemini-2.5-pro", OwnedBy: "google", Type: "gemini"},
})
defer reg.UnregisterClient("test-client-regex-2")
defer reg.UnregisterClient("test-client-regex-3")
mappings := []config.AmpModelMapping{
{From: "gpt-5", To: "claude-sonnet-4"}, // exact
{From: "^gpt-5.*$", To: "gemini-2.5-pro", Regex: true}, // regex
}
mapper := NewModelMapper(mappings)
// Exact match should win over regex
result := mapper.MapModel("gpt-5")
if result != "claude-sonnet-4" {
t.Errorf("Expected claude-sonnet-4, got %s", result)
}
}
func TestModelMapper_Regex_InvalidPattern_Skipped(t *testing.T) {
// Invalid regex should be skipped and not cause panic
mappings := []config.AmpModelMapping{
{From: "(", To: "target", Regex: true},
}
mapper := NewModelMapper(mappings)
result := mapper.MapModel("anything")
if result != "" {
t.Errorf("Expected empty result due to invalid regex, got %s", result)
}
}
func TestModelMapper_Regex_CaseInsensitive(t *testing.T) {
reg := registry.GetGlobalRegistry()
reg.RegisterClient("test-client-regex-4", "claude", []*registry.ModelInfo{
{ID: "claude-sonnet-4", OwnedBy: "anthropic", Type: "claude"},
})
defer reg.UnregisterClient("test-client-regex-4")
mappings := []config.AmpModelMapping{
{From: "^CLAUDE-OPUS-.*$", To: "claude-sonnet-4", Regex: true},
}
mapper := NewModelMapper(mappings)
result := mapper.MapModel("claude-opus-4.5")
if result != "claude-sonnet-4" {
t.Errorf("Expected claude-sonnet-4, got %s", result)
}
}

View File

@@ -209,13 +209,15 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
// Resolve logs directory relative to the configuration file directory.
var requestLogger logging.RequestLogger
var toggle func(bool)
if optionState.requestLoggerFactory != nil {
requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
}
if requestLogger != nil {
engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
toggle = setter.SetEnabled
if !cfg.CommercialMode {
if optionState.requestLoggerFactory != nil {
requestLogger = optionState.requestLoggerFactory(cfg, configFilePath)
}
if requestLogger != nil {
engine.Use(middleware.RequestLoggingMiddleware(requestLogger))
if setter, ok := requestLogger.(interface{ SetEnabled(bool) }); ok {
toggle = setter.SetEnabled
}
}
}
@@ -474,6 +476,8 @@ func (s *Server) registerManagementRoutes() {
mgmt.Use(s.managementAvailabilityMiddleware(), s.mgmt.Middleware())
{
mgmt.GET("/usage", s.mgmt.GetUsageStatistics)
mgmt.GET("/usage/export", s.mgmt.ExportUsageStatistics)
mgmt.POST("/usage/import", s.mgmt.ImportUsageStatistics)
mgmt.GET("/config", s.mgmt.GetConfig)
mgmt.GET("/config.yaml", s.mgmt.GetConfigYAML)
mgmt.PUT("/config.yaml", s.mgmt.PutConfigYAML)
@@ -496,6 +500,8 @@ func (s *Server) registerManagementRoutes() {
mgmt.PATCH("/proxy-url", s.mgmt.PutProxyURL)
mgmt.DELETE("/proxy-url", s.mgmt.DeleteProxyURL)
mgmt.POST("/api-call", s.mgmt.APICall)
mgmt.GET("/quota-exceeded/switch-project", s.mgmt.GetSwitchProject)
mgmt.PUT("/quota-exceeded/switch-project", s.mgmt.PutSwitchProject)
mgmt.PATCH("/quota-exceeded/switch-project", s.mgmt.PutSwitchProject)
@@ -518,6 +524,7 @@ func (s *Server) registerManagementRoutes() {
mgmt.DELETE("/logs", s.mgmt.DeleteLogs)
mgmt.GET("/request-error-logs", s.mgmt.GetRequestErrorLogs)
mgmt.GET("/request-error-logs/:name", s.mgmt.DownloadRequestErrorLog)
mgmt.GET("/request-log-by-id/:id", s.mgmt.GetRequestLogByID)
mgmt.GET("/request-log", s.mgmt.GetRequestLog)
mgmt.PUT("/request-log", s.mgmt.PutRequestLog)
mgmt.PATCH("/request-log", s.mgmt.PutRequestLog)

View File

@@ -39,6 +39,9 @@ type Config struct {
// Debug enables or disables debug-level logging and other debug features.
Debug bool `yaml:"debug" json:"debug"`
// CommercialMode disables high-overhead HTTP middleware features to minimize per-request memory usage.
CommercialMode bool `yaml:"commercial-mode" json:"commercial-mode"`
// LoggingToFile controls whether application logs are written to rotating files or stdout.
LoggingToFile bool `yaml:"logging-to-file" json:"logging-to-file"`
@@ -144,6 +147,11 @@ type AmpModelMapping struct {
// To is the target model name to route to (e.g., "claude-sonnet-4").
// The target model must have available providers in the registry.
To string `yaml:"to" json:"to"`
// Regex indicates whether the 'from' field should be interpreted as a regular
// expression for matching model names. When true, this mapping is evaluated
// after exact matches and in the order provided. Defaults to false (exact match).
Regex bool `yaml:"regex,omitempty" json:"regex,omitempty"`
}
// AmpCode groups Amp CLI integration settings including upstream routing,
@@ -245,6 +253,9 @@ type CodexKey struct {
// ProxyURL overrides the global proxy setting for this API key if provided.
ProxyURL string `yaml:"proxy-url" json:"proxy-url"`
// Models defines upstream model names and aliases for request routing.
Models []CodexModel `yaml:"models" json:"models"`
// Headers optionally adds extra HTTP headers for requests sent with this key.
Headers map[string]string `yaml:"headers,omitempty" json:"headers,omitempty"`
@@ -252,6 +263,15 @@ type CodexKey struct {
ExcludedModels []string `yaml:"excluded-models,omitempty" json:"excluded-models,omitempty"`
}
// CodexModel describes a mapping between an alias and the actual upstream model name.
type CodexModel struct {
// Name is the upstream model identifier used when issuing requests.
Name string `yaml:"name" json:"name"`
// Alias is the client-facing model name that maps to Name.
Alias string `yaml:"alias" json:"alias"`
}
// GeminiKey represents the configuration for a Gemini API key,
// including optional overrides for upstream base URL, proxy routing, and headers.
type GeminiKey struct {
@@ -809,8 +829,8 @@ func getOrCreateMapValue(mapNode *yaml.Node, key string) *yaml.Node {
}
// mergeMappingPreserve merges keys from src into dst mapping node while preserving
// key order and comments of existing keys in dst. Unknown keys from src are appended
// to dst at the end, copying their node structure from src.
// key order and comments of existing keys in dst. New keys are only added if their
// value is non-zero to avoid polluting the config with defaults.
func mergeMappingPreserve(dst, src *yaml.Node) {
if dst == nil || src == nil {
return
@@ -821,20 +841,19 @@ func mergeMappingPreserve(dst, src *yaml.Node) {
copyNodeShallow(dst, src)
return
}
// Build a lookup of existing keys in dst
for i := 0; i+1 < len(src.Content); i += 2 {
sk := src.Content[i]
sv := src.Content[i+1]
idx := findMapKeyIndex(dst, sk.Value)
if idx >= 0 {
// Merge into existing value node
// Merge into existing value node (always update, even to zero values)
dv := dst.Content[idx+1]
mergeNodePreserve(dv, sv)
} else {
if shouldSkipEmptyCollectionOnPersist(sk.Value, sv) {
// New key: only add if value is non-zero to avoid polluting config with defaults
if isZeroValueNode(sv) {
continue
}
// Append new key/value pair by deep-copying from src
dst.Content = append(dst.Content, deepCopyNode(sk), deepCopyNode(sv))
}
}
@@ -917,32 +936,49 @@ func findMapKeyIndex(mapNode *yaml.Node, key string) int {
return -1
}
func shouldSkipEmptyCollectionOnPersist(key string, node *yaml.Node) bool {
switch key {
case "generative-language-api-key",
"gemini-api-key",
"vertex-api-key",
"claude-api-key",
"codex-api-key",
"openai-compatibility":
return isEmptyCollectionNode(node)
default:
return false
}
}
func isEmptyCollectionNode(node *yaml.Node) bool {
// isZeroValueNode returns true if the YAML node represents a zero/default value
// that should not be written as a new key to preserve config cleanliness.
// For mappings and sequences, recursively checks if all children are zero values.
func isZeroValueNode(node *yaml.Node) bool {
if node == nil {
return true
}
switch node.Kind {
case yaml.SequenceNode:
return len(node.Content) == 0
case yaml.ScalarNode:
return node.Tag == "!!null"
default:
return false
switch node.Tag {
case "!!bool":
return node.Value == "false"
case "!!int", "!!float":
return node.Value == "0" || node.Value == "0.0"
case "!!str":
return node.Value == ""
case "!!null":
return true
}
case yaml.SequenceNode:
if len(node.Content) == 0 {
return true
}
// Check if all elements are zero values
for _, child := range node.Content {
if !isZeroValueNode(child) {
return false
}
}
return true
case yaml.MappingNode:
if len(node.Content) == 0 {
return true
}
// Check if all values are zero values (values are at odd indices)
for i := 1; i < len(node.Content); i += 2 {
if !isZeroValueNode(node.Content[i]) {
return false
}
}
return true
}
return false
}
// deepCopyNode creates a deep copy of a yaml.Node graph.

View File

@@ -30,13 +30,13 @@ type SDKConfig struct {
// StreamingConfig holds server streaming behavior configuration.
type StreamingConfig struct {
// KeepAliveSeconds controls how often the server emits SSE heartbeats (": keep-alive\n\n").
// nil means default (15 seconds). <= 0 disables keep-alives.
KeepAliveSeconds *int `yaml:"keepalive-seconds,omitempty" json:"keepalive-seconds,omitempty"`
// <= 0 disables keep-alives. Default is 0.
KeepAliveSeconds int `yaml:"keepalive-seconds,omitempty" json:"keepalive-seconds,omitempty"`
// BootstrapRetries controls how many times the server may retry a streaming request before any bytes are sent,
// to allow auth rotation / transient recovery.
// nil means default (2). 0 disables bootstrap retries.
BootstrapRetries *int `yaml:"bootstrap-retries,omitempty" json:"bootstrap-retries,omitempty"`
// <= 0 disables bootstrap retries. Default is 0.
BootstrapRetries int `yaml:"bootstrap-retries,omitempty" json:"bootstrap-retries,omitempty"`
}
// AccessConfig groups request authentication providers.

View File

@@ -7,6 +7,7 @@ import (
"fmt"
"net/http"
"runtime/debug"
"strings"
"time"
"github.com/gin-gonic/gin"
@@ -14,11 +15,24 @@ import (
log "github.com/sirupsen/logrus"
)
// aiAPIPrefixes defines path prefixes for AI API requests that should have request ID tracking.
var aiAPIPrefixes = []string{
"/v1/chat/completions",
"/v1/completions",
"/v1/messages",
"/v1/responses",
"/v1beta/models/",
"/api/provider/",
}
const skipGinLogKey = "__gin_skip_request_logging__"
// GinLogrusLogger returns a Gin middleware handler that logs HTTP requests and responses
// using logrus. It captures request details including method, path, status code, latency,
// client IP, and any error messages, formatting them in a Gin-style log format.
// client IP, and any error messages. Request ID is only added for AI API requests.
//
// Output format (AI API): [2025-12-23 20:14:10] [info ] | a1b2c3d4 | 200 | 23.559s | ...
// Output format (others): [2025-12-23 20:14:10] [info ] | -------- | 200 | 23.559s | ...
//
// Returns:
// - gin.HandlerFunc: A middleware handler for request logging
@@ -28,6 +42,15 @@ func GinLogrusLogger() gin.HandlerFunc {
path := c.Request.URL.Path
raw := util.MaskSensitiveQuery(c.Request.URL.RawQuery)
// Only generate request ID for AI API paths
var requestID string
if isAIAPIPath(path) {
requestID = GenerateRequestID()
SetGinRequestID(c, requestID)
ctx := WithRequestID(c.Request.Context(), requestID)
c.Request = c.Request.WithContext(ctx)
}
c.Next()
if shouldSkipGinRequestLogging(c) {
@@ -49,23 +72,38 @@ func GinLogrusLogger() gin.HandlerFunc {
clientIP := c.ClientIP()
method := c.Request.Method
errorMessage := c.Errors.ByType(gin.ErrorTypePrivate).String()
timestamp := time.Now().Format("2006/01/02 - 15:04:05")
logLine := fmt.Sprintf("[GIN] %s | %3d | %13v | %15s | %-7s \"%s\"", timestamp, statusCode, latency, clientIP, method, path)
if requestID == "" {
requestID = "--------"
}
logLine := fmt.Sprintf("%3d | %13v | %15s | %-7s \"%s\"", statusCode, latency, clientIP, method, path)
if errorMessage != "" {
logLine = logLine + " | " + errorMessage
}
entry := log.WithField("request_id", requestID)
switch {
case statusCode >= http.StatusInternalServerError:
log.Error(logLine)
entry.Error(logLine)
case statusCode >= http.StatusBadRequest:
log.Warn(logLine)
entry.Warn(logLine)
default:
log.Info(logLine)
entry.Info(logLine)
}
}
}
// isAIAPIPath checks if the given path is an AI API endpoint that should have request ID tracking.
func isAIAPIPath(path string) bool {
for _, prefix := range aiAPIPrefixes {
if strings.HasPrefix(path, prefix) {
return true
}
}
return false
}
// GinLogrusRecovery returns a Gin middleware handler that recovers from panics and logs
// them using logrus. When a panic occurs, it captures the panic value, stack trace,
// and request path, then returns a 500 Internal Server Error response to the client.

View File

@@ -24,7 +24,8 @@ var (
)
// LogFormatter defines a custom log format for logrus.
// This formatter adds timestamp, level, and source location to each log entry.
// This formatter adds timestamp, level, request ID, and source location to each log entry.
// Format: [2025-12-23 20:14:04] [debug] [manager.go:524] | a1b2c3d4 | Use API key sk-9...0RHO for model gpt-5.2
type LogFormatter struct{}
// Format renders a single log entry with custom formatting.
@@ -39,11 +40,22 @@ func (m *LogFormatter) Format(entry *log.Entry) ([]byte, error) {
timestamp := entry.Time.Format("2006-01-02 15:04:05")
message := strings.TrimRight(entry.Message, "\r\n")
reqID := "--------"
if id, ok := entry.Data["request_id"].(string); ok && id != "" {
reqID = id
}
level := entry.Level.String()
if level == "warning" {
level = "warn"
}
levelStr := fmt.Sprintf("%-5s", level)
var formatted string
if entry.Caller != nil {
formatted = fmt.Sprintf("[%s] [%s] [%s:%d] %s\n", timestamp, entry.Level, filepath.Base(entry.Caller.File), entry.Caller.Line, message)
formatted = fmt.Sprintf("[%s] [%s] [%s] [%s:%d] %s\n", timestamp, reqID, levelStr, filepath.Base(entry.Caller.File), entry.Caller.Line, message)
} else {
formatted = fmt.Sprintf("[%s] [%s] %s\n", timestamp, entry.Level, message)
formatted = fmt.Sprintf("[%s] [%s] [%s] %s\n", timestamp, reqID, levelStr, message)
}
buffer.WriteString(formatted)

View File

@@ -43,10 +43,11 @@ type RequestLogger interface {
// - response: The raw response data
// - apiRequest: The API request data
// - apiResponse: The API response data
// - requestID: Optional request ID for log file naming
//
// Returns:
// - error: An error if logging fails, nil otherwise
LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage) error
LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, requestID string) error
// LogStreamingRequest initiates logging for a streaming request and returns a writer for chunks.
//
@@ -55,11 +56,12 @@ type RequestLogger interface {
// - method: The HTTP method
// - headers: The request headers
// - body: The request body
// - requestID: Optional request ID for log file naming
//
// Returns:
// - StreamingLogWriter: A writer for streaming response chunks
// - error: An error if logging initialization fails, nil otherwise
LogStreamingRequest(url, method string, headers map[string][]string, body []byte) (StreamingLogWriter, error)
LogStreamingRequest(url, method string, headers map[string][]string, body []byte, requestID string) (StreamingLogWriter, error)
// IsEnabled returns whether request logging is currently enabled.
//
@@ -177,20 +179,21 @@ func (l *FileRequestLogger) SetEnabled(enabled bool) {
// - response: The raw response data
// - apiRequest: The API request data
// - apiResponse: The API response data
// - requestID: Optional request ID for log file naming
//
// Returns:
// - error: An error if logging fails, nil otherwise
func (l *FileRequestLogger) LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage) error {
return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, false)
func (l *FileRequestLogger) LogRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, requestID string) error {
return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, false, requestID)
}
// LogRequestWithOptions logs a request with optional forced logging behavior.
// The force flag allows writing error logs even when regular request logging is disabled.
func (l *FileRequestLogger) LogRequestWithOptions(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool) error {
return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, force)
func (l *FileRequestLogger) LogRequestWithOptions(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool, requestID string) error {
return l.logRequest(url, method, requestHeaders, body, statusCode, responseHeaders, response, apiRequest, apiResponse, apiResponseErrors, force, requestID)
}
func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool) error {
func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[string][]string, body []byte, statusCode int, responseHeaders map[string][]string, response, apiRequest, apiResponse []byte, apiResponseErrors []*interfaces.ErrorMessage, force bool, requestID string) error {
if !l.enabled && !force {
return nil
}
@@ -200,10 +203,10 @@ func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[st
return fmt.Errorf("failed to create logs directory: %w", errEnsure)
}
// Generate filename
filename := l.generateFilename(url)
// Generate filename with request ID
filename := l.generateFilename(url, requestID)
if force && !l.enabled {
filename = l.generateErrorFilename(url)
filename = l.generateErrorFilename(url, requestID)
}
filePath := filepath.Join(l.logsDir, filename)
@@ -271,11 +274,12 @@ func (l *FileRequestLogger) logRequest(url, method string, requestHeaders map[st
// - method: The HTTP method
// - headers: The request headers
// - body: The request body
// - requestID: Optional request ID for log file naming
//
// Returns:
// - StreamingLogWriter: A writer for streaming response chunks
// - error: An error if logging initialization fails, nil otherwise
func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[string][]string, body []byte) (StreamingLogWriter, error) {
func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[string][]string, body []byte, requestID string) (StreamingLogWriter, error) {
if !l.enabled {
return &NoOpStreamingLogWriter{}, nil
}
@@ -285,8 +289,8 @@ func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[
return nil, fmt.Errorf("failed to create logs directory: %w", err)
}
// Generate filename
filename := l.generateFilename(url)
// Generate filename with request ID
filename := l.generateFilename(url, requestID)
filePath := filepath.Join(l.logsDir, filename)
requestHeaders := make(map[string][]string, len(headers))
@@ -330,8 +334,8 @@ func (l *FileRequestLogger) LogStreamingRequest(url, method string, headers map[
}
// generateErrorFilename creates a filename with an error prefix to differentiate forced error logs.
func (l *FileRequestLogger) generateErrorFilename(url string) string {
return fmt.Sprintf("error-%s", l.generateFilename(url))
func (l *FileRequestLogger) generateErrorFilename(url string, requestID ...string) string {
return fmt.Sprintf("error-%s", l.generateFilename(url, requestID...))
}
// ensureLogsDir creates the logs directory if it doesn't exist.
@@ -346,13 +350,15 @@ func (l *FileRequestLogger) ensureLogsDir() error {
}
// generateFilename creates a sanitized filename from the URL path and current timestamp.
// Format: v1-responses-2025-12-23T195811-a1b2c3d4.log
//
// Parameters:
// - url: The request URL
// - requestID: Optional request ID to include in filename
//
// Returns:
// - string: A sanitized filename for the log file
func (l *FileRequestLogger) generateFilename(url string) string {
func (l *FileRequestLogger) generateFilename(url string, requestID ...string) string {
// Extract path from URL
path := url
if strings.Contains(url, "?") {
@@ -368,12 +374,18 @@ func (l *FileRequestLogger) generateFilename(url string) string {
sanitized := l.sanitizeForFilename(path)
// Add timestamp
timestamp := time.Now().Format("2006-01-02T150405-.000000000")
timestamp = strings.Replace(timestamp, ".", "", -1)
timestamp := time.Now().Format("2006-01-02T150405")
id := requestLogID.Add(1)
// Use request ID if provided, otherwise use sequential ID
var idPart string
if len(requestID) > 0 && requestID[0] != "" {
idPart = requestID[0]
} else {
id := requestLogID.Add(1)
idPart = fmt.Sprintf("%d", id)
}
return fmt.Sprintf("%s-%s-%d.log", sanitized, timestamp, id)
return fmt.Sprintf("%s-%s-%s.log", sanitized, timestamp, idPart)
}
// sanitizeForFilename replaces characters that are not safe for filenames.

View File

@@ -0,0 +1,61 @@
package logging
import (
"context"
"crypto/rand"
"encoding/hex"
"github.com/gin-gonic/gin"
)
// requestIDKey is the context key for storing/retrieving request IDs.
type requestIDKey struct{}
// ginRequestIDKey is the Gin context key for request IDs.
const ginRequestIDKey = "__request_id__"
// GenerateRequestID creates a new 8-character hex request ID.
func GenerateRequestID() string {
b := make([]byte, 4)
if _, err := rand.Read(b); err != nil {
return "00000000"
}
return hex.EncodeToString(b)
}
// WithRequestID returns a new context with the request ID attached.
func WithRequestID(ctx context.Context, requestID string) context.Context {
return context.WithValue(ctx, requestIDKey{}, requestID)
}
// GetRequestID retrieves the request ID from the context.
// Returns empty string if not found.
func GetRequestID(ctx context.Context) string {
if ctx == nil {
return ""
}
if id, ok := ctx.Value(requestIDKey{}).(string); ok {
return id
}
return ""
}
// SetGinRequestID stores the request ID in the Gin context.
func SetGinRequestID(c *gin.Context, requestID string) {
if c != nil {
c.Set(ginRequestIDKey, requestID)
}
}
// GetGinRequestID retrieves the request ID from the Gin context.
func GetGinRequestID(c *gin.Context) string {
if c == nil {
return ""
}
if id, exists := c.Get(ginRequestIDKey); exists {
if s, ok := id.(string); ok {
return s
}
}
return ""
}

View File

@@ -727,6 +727,7 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build", Created: 1757030400},
{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905", Created: 1757030400},
{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model", Created: 1759190400, Thinking: iFlowThinkingSupport},
{ID: "glm-4.7", DisplayName: "GLM-4.7", Description: "Zhipu GLM 4.7 general model", Created: 1766448000, Thinking: iFlowThinkingSupport},
{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model", Created: 1752192000},
{ID: "kimi-k2-thinking", DisplayName: "Kimi-K2-Thinking", Description: "Moonshot Kimi K2 thinking model", Created: 1762387200},
{ID: "deepseek-v3.2-chat", DisplayName: "DeepSeek-V3.2", Description: "DeepSeek V3.2 Chat", Created: 1764576000},
@@ -740,6 +741,7 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-235b-a22b-instruct", DisplayName: "Qwen3-235B-A22B-Instruct", Description: "Qwen3 235B A22B Instruct", Created: 1753401600},
{ID: "qwen3-235b", DisplayName: "Qwen3-235B-A22B", Description: "Qwen3 235B A22B", Created: 1753401600},
{ID: "minimax-m2", DisplayName: "MiniMax-M2", Description: "MiniMax M2", Created: 1758672000},
{ID: "minimax-m2.1", DisplayName: "MiniMax-M2.1", Description: "MiniMax M2.1", Created: 1766448000, Thinking: iFlowThinkingSupport},
}
models := make([]*ModelInfo, 0, len(entries))
for _, entry := range entries {

View File

@@ -74,6 +74,9 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
}
body = applyPayloadConfig(e.cfg, req.Model, body)
// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
body = disableThinkingIfToolChoiceForced(body)
// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
body = ensureMaxTokensForThinking(req.Model, body)
@@ -185,6 +188,9 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
body = checkSystemInstructions(body)
body = applyPayloadConfig(e.cfg, req.Model, body)
// Disable thinking if tool_choice forces tool use (Anthropic API constraint)
body = disableThinkingIfToolChoiceForced(body)
// Ensure max_tokens > thinking.budget_tokens when thinking is enabled
body = ensureMaxTokensForThinking(req.Model, body)
@@ -461,6 +467,19 @@ func (e *ClaudeExecutor) injectThinkingConfig(modelName string, metadata map[str
return util.ApplyClaudeThinkingConfig(body, budget)
}
// disableThinkingIfToolChoiceForced checks if tool_choice forces tool use and disables thinking.
// Anthropic API does not allow thinking when tool_choice is set to "any" or a specific tool.
// See: https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking#important-considerations
func disableThinkingIfToolChoiceForced(body []byte) []byte {
toolChoiceType := gjson.GetBytes(body, "tool_choice.type").String()
// "auto" is allowed with thinking, but "any" or "tool" (specific tool) are not
if toolChoiceType == "any" || toolChoiceType == "tool" {
// Remove thinking configuration entirely to avoid API error
body, _ = sjson.DeleteBytes(body, "thinking")
}
return body
}
// ensureMaxTokensForThinking ensures max_tokens > thinking.budget_tokens when thinking is enabled.
// Anthropic API requires this constraint; violating it returns a 400 error.
// This function should be called after all thinking configuration is finalized.

View File

@@ -50,6 +50,16 @@ func (e *CodexExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
defer reporter.trackFailure(ctx, &err)
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
if upstreamModel == "" {
upstreamModel = req.Model
}
if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
upstreamModel = modelOverride
} else if !strings.EqualFold(upstreamModel, req.Model) {
if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
upstreamModel = modelOverride
}
}
from := opts.SourceFormat
to := sdktranslator.FromString("codex")
@@ -147,6 +157,16 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
defer reporter.trackFailure(ctx, &err)
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
if upstreamModel == "" {
upstreamModel = req.Model
}
if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
upstreamModel = modelOverride
} else if !strings.EqualFold(upstreamModel, req.Model) {
if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
upstreamModel = modelOverride
}
}
from := opts.SourceFormat
to := sdktranslator.FromString("codex")
@@ -247,12 +267,22 @@ func (e *CodexExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
func (e *CodexExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
upstreamModel := util.ResolveOriginalModel(req.Model, req.Metadata)
if upstreamModel == "" {
upstreamModel = req.Model
}
if modelOverride := e.resolveUpstreamModel(upstreamModel, auth); modelOverride != "" {
upstreamModel = modelOverride
} else if !strings.EqualFold(upstreamModel, req.Model) {
if modelOverride := e.resolveUpstreamModel(req.Model, auth); modelOverride != "" {
upstreamModel = modelOverride
}
}
from := opts.SourceFormat
to := sdktranslator.FromString("codex")
body := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), false)
modelForCounting := req.Model
modelForCounting := upstreamModel
body = ApplyReasoningEffortMetadata(body, req.Metadata, req.Model, "reasoning.effort", false)
body, _ = sjson.SetBytes(body, "model", upstreamModel)
@@ -520,3 +550,87 @@ func codexCreds(a *cliproxyauth.Auth) (apiKey, baseURL string) {
}
return
}
func (e *CodexExecutor) resolveUpstreamModel(alias string, auth *cliproxyauth.Auth) string {
trimmed := strings.TrimSpace(alias)
if trimmed == "" {
return ""
}
entry := e.resolveCodexConfig(auth)
if entry == nil {
return ""
}
normalizedModel, metadata := util.NormalizeThinkingModel(trimmed)
// Candidate names to match against configured aliases/names.
candidates := []string{strings.TrimSpace(normalizedModel)}
if !strings.EqualFold(normalizedModel, trimmed) {
candidates = append(candidates, trimmed)
}
if original := util.ResolveOriginalModel(normalizedModel, metadata); original != "" && !strings.EqualFold(original, normalizedModel) {
candidates = append(candidates, original)
}
for i := range entry.Models {
model := entry.Models[i]
name := strings.TrimSpace(model.Name)
modelAlias := strings.TrimSpace(model.Alias)
for _, candidate := range candidates {
if candidate == "" {
continue
}
if modelAlias != "" && strings.EqualFold(modelAlias, candidate) {
if name != "" {
return name
}
return candidate
}
if name != "" && strings.EqualFold(name, candidate) {
return name
}
}
}
return ""
}
func (e *CodexExecutor) resolveCodexConfig(auth *cliproxyauth.Auth) *config.CodexKey {
if auth == nil || e.cfg == nil {
return nil
}
var attrKey, attrBase string
if auth.Attributes != nil {
attrKey = strings.TrimSpace(auth.Attributes["api_key"])
attrBase = strings.TrimSpace(auth.Attributes["base_url"])
}
for i := range e.cfg.CodexKey {
entry := &e.cfg.CodexKey[i]
cfgKey := strings.TrimSpace(entry.APIKey)
cfgBase := strings.TrimSpace(entry.BaseURL)
if attrKey != "" && attrBase != "" {
if strings.EqualFold(cfgKey, attrKey) && strings.EqualFold(cfgBase, attrBase) {
return entry
}
continue
}
if attrKey != "" && strings.EqualFold(cfgKey, attrKey) {
if cfgBase == "" || strings.EqualFold(cfgBase, attrBase) {
return entry
}
}
if attrKey == "" && attrBase != "" && strings.EqualFold(cfgBase, attrBase) {
return entry
}
}
if attrKey != "" {
for i := range e.cfg.CodexKey {
entry := &e.cfg.CodexKey[i]
if strings.EqualFold(strings.TrimSpace(entry.APIKey), attrKey) {
return entry
}
}
}
return nil
}

View File

@@ -67,6 +67,7 @@ func (e *IFlowExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, re
return resp, errValidate
}
body = applyIFlowThinkingConfig(body)
body = preserveReasoningContentInMessages(body)
body = applyPayloadConfig(e.cfg, req.Model, body)
endpoint := strings.TrimSuffix(baseURL, "/") + iflowDefaultEndpoint
@@ -159,6 +160,7 @@ func (e *IFlowExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Au
return nil, errValidate
}
body = applyIFlowThinkingConfig(body)
body = preserveReasoningContentInMessages(body)
// Ensure tools array exists to avoid provider quirks similar to Qwen's behaviour.
toolsResult := gjson.GetBytes(body, "tools")
if toolsResult.Exists() && toolsResult.IsArray() && len(toolsResult.Array()) == 0 {
@@ -445,20 +447,98 @@ func ensureToolsArray(body []byte) []byte {
return updated
}
// applyIFlowThinkingConfig converts normalized reasoning_effort to iFlow chat_template_kwargs.enable_thinking.
// This should be called after NormalizeThinkingConfig has processed the payload.
// iFlow only supports boolean enable_thinking, so any non-"none" effort enables thinking.
func applyIFlowThinkingConfig(body []byte) []byte {
effort := gjson.GetBytes(body, "reasoning_effort")
if !effort.Exists() {
// preserveReasoningContentInMessages ensures reasoning_content from assistant messages in the
// conversation history is preserved when sending to iFlow models that support thinking.
// This is critical for multi-turn conversations where the model needs to see its previous
// reasoning to maintain coherent thought chains across tool calls and conversation turns.
//
// For GLM-4.7 and MiniMax-M2.1, the full assistant response (including reasoning) must be
// appended back into message history before the next call.
func preserveReasoningContentInMessages(body []byte) []byte {
model := strings.ToLower(gjson.GetBytes(body, "model").String())
// Only apply to models that support thinking with history preservation
needsPreservation := strings.HasPrefix(model, "glm-4.7") ||
strings.HasPrefix(model, "glm-4-7") ||
strings.HasPrefix(model, "minimax-m2.1") ||
strings.HasPrefix(model, "minimax-m2-1")
if !needsPreservation {
return body
}
val := strings.ToLower(strings.TrimSpace(effort.String()))
enableThinking := val != "none" && val != ""
messages := gjson.GetBytes(body, "messages")
if !messages.Exists() || !messages.IsArray() {
return body
}
body, _ = sjson.DeleteBytes(body, "reasoning_effort")
body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
// Check if any assistant message already has reasoning_content preserved
hasReasoningContent := false
messages.ForEach(func(_, msg gjson.Result) bool {
role := msg.Get("role").String()
if role == "assistant" {
rc := msg.Get("reasoning_content")
if rc.Exists() && rc.String() != "" {
hasReasoningContent = true
return false // stop iteration
}
}
return true
})
// If reasoning content is already present, the messages are properly formatted
// No need to modify - the client has correctly preserved reasoning in history
if hasReasoningContent {
log.Debugf("iflow executor: reasoning_content found in message history for %s", model)
}
return body
}
// applyIFlowThinkingConfig converts normalized reasoning_effort to model-specific thinking configurations.
// This should be called after NormalizeThinkingConfig has processed the payload.
//
// Model-specific handling:
// - GLM-4.7: Uses extra_body={"thinking": {"type": "enabled"}, "clear_thinking": false}
// - MiniMax-M2.1: Uses reasoning_split=true for OpenAI-style reasoning separation
// - Other iFlow models: Uses chat_template_kwargs.enable_thinking (boolean)
func applyIFlowThinkingConfig(body []byte) []byte {
effort := gjson.GetBytes(body, "reasoning_effort")
model := strings.ToLower(gjson.GetBytes(body, "model").String())
// Check if thinking should be enabled
val := ""
if effort.Exists() {
val = strings.ToLower(strings.TrimSpace(effort.String()))
}
enableThinking := effort.Exists() && val != "none" && val != ""
// Remove reasoning_effort as we'll convert to model-specific format
if effort.Exists() {
body, _ = sjson.DeleteBytes(body, "reasoning_effort")
}
// GLM-4.7: Use extra_body with thinking config and clear_thinking: false
if strings.HasPrefix(model, "glm-4.7") || strings.HasPrefix(model, "glm-4-7") {
if enableThinking {
body, _ = sjson.SetBytes(body, "extra_body.thinking.type", "enabled")
body, _ = sjson.SetBytes(body, "extra_body.clear_thinking", false)
}
return body
}
// MiniMax-M2.1: Use reasoning_split=true for interleaved thinking
if strings.HasPrefix(model, "minimax-m2.1") || strings.HasPrefix(model, "minimax-m2-1") {
if enableThinking {
body, _ = sjson.SetBytes(body, "reasoning_split", true)
}
return body
}
// Other iFlow models (including GLM-4.6): Use chat_template_kwargs.enable_thinking
if effort.Exists() {
body, _ = sjson.SetBytes(body, "chat_template_kwargs.enable_thinking", enableThinking)
}
return body
}

View File

@@ -19,7 +19,7 @@ type usageReporter struct {
provider string
model string
authID string
authIndex uint64
authIndex string
apiKey string
source string
requestedAt time.Time
@@ -275,6 +275,20 @@ func parseClaudeStreamUsage(line []byte) (usage.Detail, bool) {
return detail, true
}
func parseGeminiFamilyUsageDetail(node gjson.Result) usage.Detail {
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
CachedTokens: node.Get("cachedContentTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
}
func parseGeminiCLIUsage(data []byte) usage.Detail {
usageNode := gjson.ParseBytes(data)
node := usageNode.Get("response.usageMetadata")
@@ -284,16 +298,7 @@ func parseGeminiCLIUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseGeminiUsage(data []byte) usage.Detail {
@@ -305,16 +310,7 @@ func parseGeminiUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
@@ -329,16 +325,7 @@ func parseGeminiStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
@@ -353,16 +340,7 @@ func parseGeminiCLIStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
func parseAntigravityUsage(data []byte) usage.Detail {
@@ -377,16 +355,7 @@ func parseAntigravityUsage(data []byte) usage.Detail {
if !node.Exists() {
return usage.Detail{}
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail
return parseGeminiFamilyUsageDetail(node)
}
func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
@@ -404,16 +373,7 @@ func parseAntigravityStreamUsage(line []byte) (usage.Detail, bool) {
if !node.Exists() {
return usage.Detail{}, false
}
detail := usage.Detail{
InputTokens: node.Get("promptTokenCount").Int(),
OutputTokens: node.Get("candidatesTokenCount").Int(),
ReasoningTokens: node.Get("thoughtsTokenCount").Int(),
TotalTokens: node.Get("totalTokenCount").Int(),
}
if detail.TotalTokens == 0 {
detail.TotalTokens = detail.InputTokens + detail.OutputTokens + detail.ReasoningTokens
}
return detail, true
return parseGeminiFamilyUsageDetail(node), true
}
var stopChunkWithoutUsage sync.Map
@@ -522,12 +482,16 @@ func StripUsageMetadataFromJSON(rawJSON []byte) ([]byte, bool) {
cleaned := jsonBytes
var changed bool
if gjson.GetBytes(cleaned, "usageMetadata").Exists() {
if usageMetadata = gjson.GetBytes(cleaned, "usageMetadata"); usageMetadata.Exists() {
// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
cleaned, _ = sjson.SetRawBytes(cleaned, "cpaUsageMetadata", []byte(usageMetadata.Raw))
cleaned, _ = sjson.DeleteBytes(cleaned, "usageMetadata")
changed = true
}
if gjson.GetBytes(cleaned, "response.usageMetadata").Exists() {
if usageMetadata = gjson.GetBytes(cleaned, "response.usageMetadata"); usageMetadata.Exists() {
// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
cleaned, _ = sjson.SetRawBytes(cleaned, "response.cpaUsageMetadata", []byte(usageMetadata.Raw))
cleaned, _ = sjson.DeleteBytes(cleaned, "response.usageMetadata")
changed = true
}

View File

@@ -99,6 +99,14 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
// This follows the Claude Code API specification for streaming message initialization
messageStartTemplate := `{"type": "message_start", "message": {"id": "msg_1nZdL29xx5MUA1yADyHTEsnR8uuvGzszyY", "type": "message", "role": "assistant", "content": [], "model": "claude-3-5-sonnet-20241022", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 0, "output_tokens": 0}}}`
// Use cpaUsageMetadata within the message_start event for Claude.
if promptTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.promptTokenCount"); promptTokenCount.Exists() {
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.input_tokens", promptTokenCount.Int())
}
if candidatesTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.candidatesTokenCount"); candidatesTokenCount.Exists() {
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.output_tokens", candidatesTokenCount.Int())
}
// Override default values with actual response metadata if available from the Gemini CLI response
if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.model", modelVersionResult.String())
@@ -271,11 +279,11 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
params.HasUsageMetadata = true
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int()
params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() - params.CachedTokenCount
params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int()
params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int()
params.TotalTokenCount = usageResult.Get("totalTokenCount").Int()
params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
if params.CandidatesTokenCount == 0 && params.TotalTokenCount > 0 {
params.CandidatesTokenCount = params.TotalTokenCount - params.PromptTokenCount - params.ThoughtsTokenCount
if params.CandidatesTokenCount < 0 {

View File

@@ -247,10 +247,30 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
} else if role == "assistant" {
node := []byte(`{"role":"model","parts":[]}`)
p := 0
if content.Type == gjson.String {
if content.Type == gjson.String && content.String() != "" {
node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
p++
} else if content.IsArray() {
// Assistant multimodal content (e.g. text + image) -> single model content with parts
for _, item := range content.Array() {
switch item.Get("type").String() {
case "text":
p++
case "image_url":
// If the assistant returned an inline data URL, preserve it for history fidelity.
imageURL := item.Get("image_url.url").String()
if len(imageURL) > 5 { // expect data:...
pieces := strings.SplitN(imageURL[5:], ";", 2)
if len(pieces) == 2 && len(pieces[1]) > 7 {
mime := pieces[0]
data := pieces[1][7:]
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
p++
}
}
}
}
}
// Tool calls -> single model content with functionCall parts
@@ -305,6 +325,8 @@ func ConvertOpenAIRequestToAntigravity(modelName string, inputRawJSON []byte, _
if pp > 0 {
out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
}
} else {
out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
}
}
}

View File

@@ -87,15 +87,15 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
// Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
}
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
}
promptTokenCount := usageResult.Get("promptTokenCount").Int()
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
@@ -181,12 +181,14 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
mimeType = "image/png"
}
imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
imagesResult := gjson.Get(template, "choices.0.delta.images")
if !imagesResult.Exists() || !imagesResult.IsArray() {
template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
}
imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
imagePayload := `{"type":"image_url","image_url":{"url":""}}`
imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
}

View File

@@ -205,9 +205,12 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
if usage := root.Get("usage"); usage.Exists() {
inputTokens := usage.Get("input_tokens").Int()
outputTokens := usage.Get("output_tokens").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", inputTokens)
cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
template, _ = sjson.Set(template, "usage.completion_tokens", outputTokens)
template, _ = sjson.Set(template, "usage.total_tokens", inputTokens+outputTokens)
template, _ = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
}
return []string{template}
@@ -281,8 +284,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
var messageID string
var model string
var createdAt int64
var inputTokens, outputTokens int64
var reasoningTokens int64
var stopReason string
var contentParts []string
var reasoningParts []string
@@ -299,9 +300,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
messageID = message.Get("id").String()
model = message.Get("model").String()
createdAt = time.Now().Unix()
if usage := message.Get("usage"); usage.Exists() {
inputTokens = usage.Get("input_tokens").Int()
}
}
case "content_block_start":
@@ -364,11 +362,14 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
}
}
if usage := root.Get("usage"); usage.Exists() {
outputTokens = usage.Get("output_tokens").Int()
// Estimate reasoning tokens from accumulated thinking content
if len(reasoningParts) > 0 {
reasoningTokens = int64(len(strings.Join(reasoningParts, "")) / 4) // Rough estimation
}
inputTokens := usage.Get("input_tokens").Int()
outputTokens := usage.Get("output_tokens").Int()
cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
out, _ = sjson.Set(out, "usage.total_tokens", inputTokens+outputTokens)
out, _ = sjson.Set(out, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
}
}
}
@@ -427,16 +428,5 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
out, _ = sjson.Set(out, "choices.0.finish_reason", mapAnthropicStopReasonToOpenAI(stopReason))
}
// Set usage information including prompt tokens, completion tokens, and total tokens
totalTokens := inputTokens + outputTokens
out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens)
out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
out, _ = sjson.Set(out, "usage.total_tokens", totalTokens)
// Add reasoning tokens to usage details if any reasoning content was processed
if reasoningTokens > 0 {
out, _ = sjson.Set(out, "usage.completion_tokens_details.reasoning_tokens", reasoningTokens)
}
return out
}

View File

@@ -114,13 +114,16 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
var builder strings.Builder
if parts := item.Get("content"); parts.Exists() && parts.IsArray() {
parts.ForEach(func(_, part gjson.Result) bool {
text := part.Get("text").String()
textResult := part.Get("text")
text := textResult.String()
if builder.Len() > 0 && text != "" {
builder.WriteByte('\n')
}
builder.WriteString(text)
return true
})
} else if parts.Type == gjson.String {
builder.WriteString(parts.String())
}
instructionsText = builder.String()
if instructionsText != "" {
@@ -207,6 +210,8 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
}
return true
})
} else if parts.Type == gjson.String {
textAggregate.WriteString(parts.String())
}
// Fallback to given role if content types not decisive

View File

@@ -218,8 +218,29 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
if content.Type == gjson.String {
// Assistant text -> single model content
node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
p++
} else if content.IsArray() {
// Assistant multimodal content (e.g. text + image) -> single model content with parts
for _, item := range content.Array() {
switch item.Get("type").String() {
case "text":
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
p++
case "image_url":
// If the assistant returned an inline data URL, preserve it for history fidelity.
imageURL := item.Get("image_url.url").String()
if len(imageURL) > 5 { // expect data:...
pieces := strings.SplitN(imageURL[5:], ";", 2)
if len(pieces) == 2 && len(pieces[1]) > 7 {
mime := pieces[0]
data := pieces[1][7:]
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.mime_type", mime)
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".inlineData.data", data)
p++
}
}
}
}
}
// Tool calls -> single model content with functionCall parts
@@ -260,6 +281,8 @@ func ConvertOpenAIRequestToGeminiCLI(modelName string, inputRawJSON []byte, _ bo
if pp > 0 {
out, _ = sjson.SetRawBytes(out, "request.contents.-1", toolNode)
}
} else {
out, _ = sjson.SetRawBytes(out, "request.contents.-1", node)
}
}
}

View File

@@ -170,12 +170,14 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
mimeType = "image/png"
}
imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
imagesResult := gjson.Get(template, "choices.0.delta.images")
if !imagesResult.Exists() || !imagesResult.IsArray() {
template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
}
imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
imagePayload := `{"type":"image_url","image_url":{"url":""}}`
imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
}

View File

@@ -233,18 +233,15 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
} else if role == "assistant" {
node := []byte(`{"role":"model","parts":[]}`)
p := 0
if content.Type == gjson.String {
// Assistant text -> single model content
node, _ = sjson.SetBytes(node, "parts.-1.text", content.String())
out, _ = sjson.SetRawBytes(out, "contents.-1", node)
p++
} else if content.IsArray() {
// Assistant multimodal content (e.g. text + image) -> single model content with parts
for _, item := range content.Array() {
switch item.Get("type").String() {
case "text":
node, _ = sjson.SetBytes(node, "parts."+itoa(p)+".text", item.Get("text").String())
p++
case "image_url":
// If the assistant returned an inline data URL, preserve it for history fidelity.
@@ -261,7 +258,6 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
}
}
}
out, _ = sjson.SetRawBytes(out, "contents.-1", node)
}
// Tool calls -> single model content with functionCall parts
@@ -302,6 +298,8 @@ func ConvertOpenAIRequestToGemini(modelName string, inputRawJSON []byte, _ bool)
if pp > 0 {
out, _ = sjson.SetRawBytes(out, "contents.-1", toolNode)
}
} else {
out, _ = sjson.SetRawBytes(out, "contents.-1", node)
}
}
}

View File

@@ -89,15 +89,15 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
// Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
}
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
}
promptTokenCount := usageResult.Get("promptTokenCount").Int()
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
@@ -182,12 +182,14 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
mimeType = "image/png"
}
imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
imagesResult := gjson.Get(template, "choices.0.delta.images")
if !imagesResult.Exists() || !imagesResult.IsArray() {
template, _ = sjson.SetRaw(template, "choices.0.delta.images", `[]`)
}
imageIndex := len(gjson.Get(template, "choices.0.delta.images").Array())
imagePayload := `{"type":"image_url","image_url":{"url":""}}`
imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
template, _ = sjson.SetRaw(template, "choices.0.delta.images.-1", imagePayload)
}
@@ -316,12 +318,14 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
mimeType = "image/png"
}
imageURL := fmt.Sprintf("data:%s;base64,%s", mimeType, data)
imagePayload := `{"image_url":{"url":""},"type":"image_url"}`
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
imagesResult := gjson.Get(template, "choices.0.message.images")
if !imagesResult.Exists() || !imagesResult.IsArray() {
template, _ = sjson.SetRaw(template, "choices.0.message.images", `[]`)
}
imageIndex := len(gjson.Get(template, "choices.0.message.images").Array())
imagePayload := `{"type":"image_url","image_url":{"url":""}}`
imagePayload, _ = sjson.Set(imagePayload, "index", imageIndex)
imagePayload, _ = sjson.Set(imagePayload, "image_url.url", imageURL)
template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
template, _ = sjson.SetRaw(template, "choices.0.message.images.-1", imagePayload)
}

View File

@@ -6,6 +6,7 @@ package usage
import (
"context"
"fmt"
"strings"
"sync"
"sync/atomic"
"time"
@@ -90,7 +91,7 @@ type modelStats struct {
type RequestDetail struct {
Timestamp time.Time `json:"timestamp"`
Source string `json:"source"`
AuthIndex uint64 `json:"auth_index"`
AuthIndex string `json:"auth_index"`
Tokens TokenStats `json:"tokens"`
Failed bool `json:"failed"`
}
@@ -281,6 +282,118 @@ func (s *RequestStatistics) Snapshot() StatisticsSnapshot {
return result
}
type MergeResult struct {
Added int64 `json:"added"`
Skipped int64 `json:"skipped"`
}
// MergeSnapshot merges an exported statistics snapshot into the current store.
// Existing data is preserved and duplicate request details are skipped.
func (s *RequestStatistics) MergeSnapshot(snapshot StatisticsSnapshot) MergeResult {
result := MergeResult{}
if s == nil {
return result
}
s.mu.Lock()
defer s.mu.Unlock()
seen := make(map[string]struct{})
for apiName, stats := range s.apis {
if stats == nil {
continue
}
for modelName, modelStatsValue := range stats.Models {
if modelStatsValue == nil {
continue
}
for _, detail := range modelStatsValue.Details {
seen[dedupKey(apiName, modelName, detail)] = struct{}{}
}
}
}
for apiName, apiSnapshot := range snapshot.APIs {
apiName = strings.TrimSpace(apiName)
if apiName == "" {
continue
}
stats, ok := s.apis[apiName]
if !ok || stats == nil {
stats = &apiStats{Models: make(map[string]*modelStats)}
s.apis[apiName] = stats
} else if stats.Models == nil {
stats.Models = make(map[string]*modelStats)
}
for modelName, modelSnapshot := range apiSnapshot.Models {
modelName = strings.TrimSpace(modelName)
if modelName == "" {
modelName = "unknown"
}
for _, detail := range modelSnapshot.Details {
detail.Tokens = normaliseTokenStats(detail.Tokens)
if detail.Timestamp.IsZero() {
detail.Timestamp = time.Now()
}
key := dedupKey(apiName, modelName, detail)
if _, exists := seen[key]; exists {
result.Skipped++
continue
}
seen[key] = struct{}{}
s.recordImported(apiName, modelName, stats, detail)
result.Added++
}
}
}
return result
}
func (s *RequestStatistics) recordImported(apiName, modelName string, stats *apiStats, detail RequestDetail) {
totalTokens := detail.Tokens.TotalTokens
if totalTokens < 0 {
totalTokens = 0
}
s.totalRequests++
if detail.Failed {
s.failureCount++
} else {
s.successCount++
}
s.totalTokens += totalTokens
s.updateAPIStats(stats, modelName, detail)
dayKey := detail.Timestamp.Format("2006-01-02")
hourKey := detail.Timestamp.Hour()
s.requestsByDay[dayKey]++
s.requestsByHour[hourKey]++
s.tokensByDay[dayKey] += totalTokens
s.tokensByHour[hourKey] += totalTokens
}
func dedupKey(apiName, modelName string, detail RequestDetail) string {
timestamp := detail.Timestamp.UTC().Format(time.RFC3339Nano)
tokens := normaliseTokenStats(detail.Tokens)
return fmt.Sprintf(
"%s|%s|%s|%s|%s|%t|%d|%d|%d|%d|%d",
apiName,
modelName,
timestamp,
detail.Source,
detail.AuthIndex,
detail.Failed,
tokens.InputTokens,
tokens.OutputTokens,
tokens.ReasoningTokens,
tokens.CachedTokens,
tokens.TotalTokens,
)
}
func resolveAPIIdentifier(ctx context.Context, record coreusage.Record) string {
if ctx != nil {
if ginCtx, ok := ctx.Value("gin").(*gin.Context); ok && ginCtx != nil {
@@ -340,6 +453,16 @@ func normaliseDetail(detail coreusage.Detail) TokenStats {
return tokens
}
func normaliseTokenStats(tokens TokenStats) TokenStats {
if tokens.TotalTokens == 0 {
tokens.TotalTokens = tokens.InputTokens + tokens.OutputTokens + tokens.ReasoningTokens
}
if tokens.TotalTokens == 0 {
tokens.TotalTokens = tokens.InputTokens + tokens.OutputTokens + tokens.ReasoningTokens + tokens.CachedTokens
}
return tokens
}
func formatHour(hour int) string {
if hour < 0 {
hour = 0

View File

@@ -56,6 +56,21 @@ func ComputeClaudeModelsHash(models []config.ClaudeModel) string {
return hashJoined(keys)
}
// ComputeCodexModelsHash returns a stable hash for Codex model aliases.
func ComputeCodexModelsHash(models []config.CodexModel) string {
keys := normalizeModelPairs(func(out func(key string)) {
for _, model := range models {
name := strings.TrimSpace(model.Name)
alias := strings.TrimSpace(model.Alias)
if name == "" && alias == "" {
continue
}
out(strings.ToLower(name) + "|" + strings.ToLower(alias))
}
})
return hashJoined(keys)
}
// ComputeExcludedModelsHash returns a normalized hash for excluded model lists.
func ComputeExcludedModelsHash(excluded []string) string {
if len(excluded) == 0 {

View File

@@ -81,6 +81,15 @@ func TestComputeClaudeModelsHash_Empty(t *testing.T) {
}
}
func TestComputeCodexModelsHash_Empty(t *testing.T) {
if got := ComputeCodexModelsHash(nil); got != "" {
t.Fatalf("expected empty hash for nil models, got %q", got)
}
if got := ComputeCodexModelsHash([]config.CodexModel{}); got != "" {
t.Fatalf("expected empty hash for empty slice, got %q", got)
}
}
func TestComputeClaudeModelsHash_IgnoresBlankAndDedup(t *testing.T) {
a := []config.ClaudeModel{
{Name: "m1", Alias: "a1"},
@@ -95,6 +104,20 @@ func TestComputeClaudeModelsHash_IgnoresBlankAndDedup(t *testing.T) {
}
}
func TestComputeCodexModelsHash_IgnoresBlankAndDedup(t *testing.T) {
a := []config.CodexModel{
{Name: "m1", Alias: "a1"},
{Name: " "},
{Name: "M1", Alias: "A1"},
}
b := []config.CodexModel{
{Name: "m1", Alias: "a1"},
}
if h1, h2 := ComputeCodexModelsHash(a), ComputeCodexModelsHash(b); h1 == "" || h1 != h2 {
t.Fatalf("expected same hash ignoring blanks/dupes, got %q / %q", h1, h2)
}
}
func TestComputeExcludedModelsHash_Normalizes(t *testing.T) {
hash1 := ComputeExcludedModelsHash([]string{" A ", "b", "a"})
hash2 := ComputeExcludedModelsHash([]string{"a", " b", "A"})
@@ -157,3 +180,15 @@ func TestComputeClaudeModelsHash_Deterministic(t *testing.T) {
t.Fatalf("expected different hash when models change, got %s", h3)
}
}
func TestComputeCodexModelsHash_Deterministic(t *testing.T) {
models := []config.CodexModel{{Name: "a", Alias: "A"}, {Name: "b"}}
h1 := ComputeCodexModelsHash(models)
h2 := ComputeCodexModelsHash(models)
if h1 == "" || h1 != h2 {
t.Fatalf("expected deterministic hash, got %s / %s", h1, h2)
}
if h3 := ComputeCodexModelsHash([]config.CodexModel{{Name: "a"}}); h3 == h1 {
t.Fatalf("expected different hash when models change, got %s", h3)
}
}

View File

@@ -147,6 +147,9 @@ func (s *ConfigSynthesizer) synthesizeCodexKeys(ctx *SynthesisContext) []*coreau
if ck.BaseURL != "" {
attrs["base_url"] = ck.BaseURL
}
if hash := diff.ComputeCodexModelsHash(ck.Models); hash != "" {
attrs["models_hash"] = hash
}
addConfigHeadersToAttrs(ck.Headers, attrs)
proxyURL := strings.TrimSpace(ck.ProxyURL)
a := &coreauth.Auth{

View File

@@ -14,6 +14,7 @@ import (
"github.com/gin-gonic/gin"
"github.com/google/uuid"
"github.com/router-for-me/CLIProxyAPI/v6/internal/interfaces"
"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
coreexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
@@ -103,8 +104,8 @@ func BuildErrorResponseBody(status int, errText string) []byte {
// Returning 0 disables keep-alives (default when unset).
func StreamingKeepAliveInterval(cfg *config.SDKConfig) time.Duration {
seconds := defaultStreamingKeepAliveSeconds
if cfg != nil && cfg.Streaming.KeepAliveSeconds != nil {
seconds = *cfg.Streaming.KeepAliveSeconds
if cfg != nil {
seconds = cfg.Streaming.KeepAliveSeconds
}
if seconds <= 0 {
return 0
@@ -115,8 +116,8 @@ func StreamingKeepAliveInterval(cfg *config.SDKConfig) time.Duration {
// StreamingBootstrapRetries returns how many times a streaming request may be retried before any bytes are sent.
func StreamingBootstrapRetries(cfg *config.SDKConfig) int {
retries := defaultStreamingBootstrapRetries
if cfg != nil && cfg.Streaming.BootstrapRetries != nil {
retries = *cfg.Streaming.BootstrapRetries
if cfg != nil {
retries = cfg.Streaming.BootstrapRetries
}
if retries < 0 {
retries = 0
@@ -216,13 +217,39 @@ func (h *BaseAPIHandler) GetAlt(c *gin.Context) string {
// Parameters:
// - handler: The API handler associated with the request.
// - c: The Gin context of the current request.
// - ctx: The parent context.
// - ctx: The parent context (caller values/deadlines are preserved; request context adds cancellation and request ID).
//
// Returns:
// - context.Context: The new context with cancellation and embedded values.
// - APIHandlerCancelFunc: A function to cancel the context and log the response.
func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *gin.Context, ctx context.Context) (context.Context, APIHandlerCancelFunc) {
newCtx, cancel := context.WithCancel(ctx)
parentCtx := ctx
if parentCtx == nil {
parentCtx = context.Background()
}
var requestCtx context.Context
if c != nil && c.Request != nil {
requestCtx = c.Request.Context()
}
if requestCtx != nil && logging.GetRequestID(parentCtx) == "" {
if requestID := logging.GetRequestID(requestCtx); requestID != "" {
parentCtx = logging.WithRequestID(parentCtx, requestID)
} else if requestID := logging.GetGinRequestID(c); requestID != "" {
parentCtx = logging.WithRequestID(parentCtx, requestID)
}
}
newCtx, cancel := context.WithCancel(parentCtx)
if requestCtx != nil && requestCtx != parentCtx {
go func() {
select {
case <-requestCtx.Done():
cancel()
case <-newCtx.Done():
}
}()
}
newCtx = context.WithValue(newCtx, "gin", c)
newCtx = context.WithValue(newCtx, "handler", handler)
return newCtx, func(params ...interface{}) {

View File

@@ -94,12 +94,11 @@ func TestExecuteStreamWithAuthManager_RetriesBeforeFirstByte(t *testing.T) {
registry.GetGlobalRegistry().UnregisterClient(auth2.ID)
})
bootstrapRetries := 1
handler := NewBaseAPIHandlers(&sdkconfig.SDKConfig{
Streaming: sdkconfig.StreamingConfig{
BootstrapRetries: &bootstrapRetries,
BootstrapRetries: 1,
},
}, manager, nil)
}, manager)
dataChan, errChan := handler.ExecuteStreamWithAuthManager(context.Background(), "openai", "test-model", []byte(`{"model":"test-model"}`), "")
if dataChan == nil || errChan == nil {
t.Fatalf("expected non-nil channels")

62
sdk/api/management.go Normal file
View File

@@ -0,0 +1,62 @@
// Package api exposes helpers for embedding CLIProxyAPI.
//
// It wraps internal management handler types so external projects can integrate
// management endpoints without importing internal packages.
package api
import (
"github.com/gin-gonic/gin"
internalmanagement "github.com/router-for-me/CLIProxyAPI/v6/internal/api/handlers/management"
coreauth "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/auth"
"github.com/router-for-me/CLIProxyAPI/v6/sdk/config"
)
// ManagementTokenRequester exposes a limited subset of management endpoints for requesting tokens.
type ManagementTokenRequester interface {
RequestAnthropicToken(*gin.Context)
RequestGeminiCLIToken(*gin.Context)
RequestCodexToken(*gin.Context)
RequestAntigravityToken(*gin.Context)
RequestQwenToken(*gin.Context)
RequestIFlowToken(*gin.Context)
RequestIFlowCookieToken(*gin.Context)
}
type managementTokenRequester struct {
handler *internalmanagement.Handler
}
// NewManagementTokenRequester creates a limited management handler exposing only token request endpoints.
func NewManagementTokenRequester(cfg *config.Config, manager *coreauth.Manager) ManagementTokenRequester {
return &managementTokenRequester{
handler: internalmanagement.NewHandlerWithoutConfigFilePath(cfg, manager),
}
}
func (m *managementTokenRequester) RequestAnthropicToken(c *gin.Context) {
m.handler.RequestAnthropicToken(c)
}
func (m *managementTokenRequester) RequestGeminiCLIToken(c *gin.Context) {
m.handler.RequestGeminiCLIToken(c)
}
func (m *managementTokenRequester) RequestCodexToken(c *gin.Context) {
m.handler.RequestCodexToken(c)
}
func (m *managementTokenRequester) RequestAntigravityToken(c *gin.Context) {
m.handler.RequestAntigravityToken(c)
}
func (m *managementTokenRequester) RequestQwenToken(c *gin.Context) {
m.handler.RequestQwenToken(c)
}
func (m *managementTokenRequester) RequestIFlowToken(c *gin.Context) {
m.handler.RequestIFlowToken(c)
}
func (m *managementTokenRequester) RequestIFlowCookieToken(c *gin.Context) {
m.handler.RequestIFlowCookieToken(c)
}

View File

@@ -12,6 +12,7 @@ import (
"time"
"github.com/google/uuid"
"github.com/router-for-me/CLIProxyAPI/v6/internal/logging"
"github.com/router-for-me/CLIProxyAPI/v6/internal/registry"
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
cliproxyexecutor "github.com/router-for-me/CLIProxyAPI/v6/sdk/cliproxy/executor"
@@ -202,10 +203,10 @@ func (m *Manager) Register(ctx context.Context, auth *Auth) (*Auth, error) {
if auth == nil {
return nil, nil
}
auth.EnsureIndex()
if auth.ID == "" {
auth.ID = uuid.NewString()
}
auth.EnsureIndex()
m.mu.Lock()
m.auths[auth.ID] = auth.Clone()
m.mu.Unlock()
@@ -220,7 +221,7 @@ func (m *Manager) Update(ctx context.Context, auth *Auth) (*Auth, error) {
return nil, nil
}
m.mu.Lock()
if existing, ok := m.auths[auth.ID]; ok && existing != nil && !auth.indexAssigned && auth.Index == 0 {
if existing, ok := m.auths[auth.ID]; ok && existing != nil && !auth.indexAssigned && auth.Index == "" {
auth.Index = existing.Index
auth.indexAssigned = existing.indexAssigned
}
@@ -262,7 +263,6 @@ func (m *Manager) Execute(ctx context.Context, providers []string, req cliproxye
return cliproxyexecutor.Response{}, &Error{Code: "provider_not_found", Message: "no provider supplied"}
}
rotated := m.rotateProviders(req.Model, normalized)
defer m.advanceProviderCursor(req.Model, normalized)
retryTimes, maxWait := m.retrySettings()
attempts := retryTimes + 1
@@ -301,7 +301,6 @@ func (m *Manager) ExecuteCount(ctx context.Context, providers []string, req clip
return cliproxyexecutor.Response{}, &Error{Code: "provider_not_found", Message: "no provider supplied"}
}
rotated := m.rotateProviders(req.Model, normalized)
defer m.advanceProviderCursor(req.Model, normalized)
retryTimes, maxWait := m.retrySettings()
attempts := retryTimes + 1
@@ -340,7 +339,6 @@ func (m *Manager) ExecuteStream(ctx context.Context, providers []string, req cli
return nil, &Error{Code: "provider_not_found", Message: "no provider supplied"}
}
rotated := m.rotateProviders(req.Model, normalized)
defer m.advanceProviderCursor(req.Model, normalized)
retryTimes, maxWait := m.retrySettings()
attempts := retryTimes + 1
@@ -389,17 +387,18 @@ func (m *Manager) executeWithProvider(ctx context.Context, provider string, req
accountType, accountInfo := auth.AccountInfo()
proxyInfo := auth.ProxyInfo()
entry := logEntryWithRequestID(ctx)
if accountType == "api_key" {
if proxyInfo != "" {
log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
entry.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
} else {
log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
entry.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
}
} else if accountType == "oauth" {
if proxyInfo != "" {
log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
entry.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
} else {
log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
entry.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
}
}
@@ -449,17 +448,18 @@ func (m *Manager) executeCountWithProvider(ctx context.Context, provider string,
accountType, accountInfo := auth.AccountInfo()
proxyInfo := auth.ProxyInfo()
entry := logEntryWithRequestID(ctx)
if accountType == "api_key" {
if proxyInfo != "" {
log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
entry.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
} else {
log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
entry.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
}
} else if accountType == "oauth" {
if proxyInfo != "" {
log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
entry.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
} else {
log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
entry.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
}
}
@@ -509,17 +509,18 @@ func (m *Manager) executeStreamWithProvider(ctx context.Context, provider string
accountType, accountInfo := auth.AccountInfo()
proxyInfo := auth.ProxyInfo()
entry := logEntryWithRequestID(ctx)
if accountType == "api_key" {
if proxyInfo != "" {
log.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
entry.Debugf("Use API key %s for model %s %s", util.HideAPIKey(accountInfo), req.Model, proxyInfo)
} else {
log.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
entry.Debugf("Use API key %s for model %s", util.HideAPIKey(accountInfo), req.Model)
}
} else if accountType == "oauth" {
if proxyInfo != "" {
log.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
entry.Debugf("Use OAuth %s for model %s %s", accountInfo, req.Model, proxyInfo)
} else {
log.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
entry.Debugf("Use OAuth %s for model %s", accountInfo, req.Model)
}
}
@@ -636,13 +637,20 @@ func (m *Manager) normalizeProviders(providers []string) []string {
return result
}
// rotateProviders returns a rotated view of the providers list starting from the
// current offset for the model, and atomically increments the offset for the next call.
// This ensures concurrent requests get different starting providers.
func (m *Manager) rotateProviders(model string, providers []string) []string {
if len(providers) == 0 {
return nil
}
m.mu.RLock()
// Atomic read-and-increment: get current offset and advance cursor in one lock
m.mu.Lock()
offset := m.providerOffsets[model]
m.mu.RUnlock()
m.providerOffsets[model] = (offset + 1) % len(providers)
m.mu.Unlock()
if len(providers) > 0 {
offset %= len(providers)
}
@@ -658,19 +666,6 @@ func (m *Manager) rotateProviders(model string, providers []string) []string {
return rotated
}
func (m *Manager) advanceProviderCursor(model string, providers []string) {
if len(providers) == 0 {
m.mu.Lock()
delete(m.providerOffsets, model)
m.mu.Unlock()
return
}
m.mu.Lock()
current := m.providerOffsets[model]
m.providerOffsets[model] = (current + 1) % len(providers)
m.mu.Unlock()
}
func (m *Manager) retrySettings() (int, time.Duration) {
if m == nil {
return 0, 0
@@ -1604,6 +1599,17 @@ type RequestPreparer interface {
PrepareRequest(req *http.Request, auth *Auth) error
}
// logEntryWithRequestID returns a logrus entry with request_id field if available in context.
func logEntryWithRequestID(ctx context.Context) *log.Entry {
if ctx == nil {
return log.NewEntry(log.StandardLogger())
}
if reqID := logging.GetRequestID(ctx); reqID != "" {
return log.WithField("request_id", reqID)
}
return log.NewEntry(log.StandardLogger())
}
// InjectCredentials delegates per-provider HTTP request preparation when supported.
// If the registered executor for the auth provider implements RequestPreparer,
// it will be invoked to modify the request (e.g., add headers).

View File

@@ -1,11 +1,12 @@
package auth
import (
"crypto/sha256"
"encoding/hex"
"encoding/json"
"strconv"
"strings"
"sync"
"sync/atomic"
"time"
baseauth "github.com/router-for-me/CLIProxyAPI/v6/internal/auth"
@@ -15,8 +16,8 @@ import (
type Auth struct {
// ID uniquely identifies the auth record across restarts.
ID string `json:"id"`
// Index is a monotonically increasing runtime identifier used for diagnostics.
Index uint64 `json:"-"`
// Index is a stable runtime identifier derived from auth metadata (not persisted).
Index string `json:"-"`
// Provider is the upstream provider key (e.g. "gemini", "claude").
Provider string `json:"provider"`
// Prefix optionally namespaces models for routing (e.g., "teamA/gemini-3-pro-preview").
@@ -94,12 +95,6 @@ type ModelState struct {
UpdatedAt time.Time `json:"updated_at"`
}
var authIndexCounter atomic.Uint64
func nextAuthIndex() uint64 {
return authIndexCounter.Add(1) - 1
}
// Clone shallow copies the Auth structure, duplicating maps to avoid accidental mutation.
func (a *Auth) Clone() *Auth {
if a == nil {
@@ -128,15 +123,41 @@ func (a *Auth) Clone() *Auth {
return &copyAuth
}
// EnsureIndex returns the global index, assigning one if it was not set yet.
func (a *Auth) EnsureIndex() uint64 {
if a == nil {
return 0
func stableAuthIndex(seed string) string {
seed = strings.TrimSpace(seed)
if seed == "" {
return ""
}
if a.indexAssigned {
sum := sha256.Sum256([]byte(seed))
return hex.EncodeToString(sum[:8])
}
// EnsureIndex returns a stable index derived from the auth file name or API key.
func (a *Auth) EnsureIndex() string {
if a == nil {
return ""
}
if a.indexAssigned && a.Index != "" {
return a.Index
}
idx := nextAuthIndex()
seed := strings.TrimSpace(a.FileName)
if seed != "" {
seed = "file:" + seed
} else if a.Attributes != nil {
if apiKey := strings.TrimSpace(a.Attributes["api_key"]); apiKey != "" {
seed = "api_key:" + apiKey
}
}
if seed == "" {
if id := strings.TrimSpace(a.ID); id != "" {
seed = "id:" + id
} else {
return ""
}
}
idx := stableAuthIndex(seed)
a.Index = idx
a.indexAssigned = true
return idx

View File

@@ -741,6 +741,9 @@ func (s *Service) registerModelsForAuth(a *coreauth.Auth) {
case "codex":
models = registry.GetOpenAIModels()
if entry := s.resolveConfigCodexKey(a); entry != nil {
if len(entry.Models) > 0 {
models = buildCodexConfigModels(entry)
}
if authKind == "apikey" {
excluded = entry.ExcludedModels
}
@@ -1179,3 +1182,41 @@ func buildClaudeConfigModels(entry *config.ClaudeKey) []*ModelInfo {
}
return out
}
func buildCodexConfigModels(entry *config.CodexKey) []*ModelInfo {
if entry == nil || len(entry.Models) == 0 {
return nil
}
now := time.Now().Unix()
out := make([]*ModelInfo, 0, len(entry.Models))
seen := make(map[string]struct{}, len(entry.Models))
for i := range entry.Models {
model := entry.Models[i]
name := strings.TrimSpace(model.Name)
alias := strings.TrimSpace(model.Alias)
if alias == "" {
alias = name
}
if alias == "" {
continue
}
key := strings.ToLower(alias)
if _, exists := seen[key]; exists {
continue
}
seen[key] = struct{}{}
display := name
if display == "" {
display = alias
}
out = append(out, &ModelInfo{
ID: alias,
Object: "model",
Created: now,
OwnedBy: "openai",
Type: "openai",
DisplayName: display,
})
}
return out
}

View File

@@ -14,7 +14,7 @@ type Record struct {
Model string
APIKey string
AuthID string
AuthIndex uint64
AuthIndex string
Source string
RequestedAt time.Time
Failed bool