Commit Graph

67 Commits

Author SHA1 Message Date
Luis Pater
771fec9447 Merge branch 'main' into plus 2026-01-04 01:38:40 +08:00
Luis Pater
7a77b23f2d feat(executor): add token refresh timeout and improve context handling during refresh
Introduced `tokenRefreshTimeout` constant for token refresh operations and enhanced context propagation for `refreshToken` by embedding roundtrip information if available. Adjusted `refreshAuth` to ensure default context initialization and handle cancellation errors appropriately.
2026-01-04 00:26:08 +08:00
Luis Pater
ba486ca6b7 Merge branch 'router-for-me:main' into main 2026-01-01 21:03:16 +08:00
hkfires
89db4e9481 fix(thinking): use model alias for thinking config resolution in mapped models 2025-12-31 17:09:22 +08:00
Luis Pater
e85c9d9322 Merge branch 'main' into plus 2025-12-30 23:33:35 +08:00
hkfires
96340bf136 refactor(executor): resolve upstream model at conductor level before execution 2025-12-30 19:31:54 +08:00
Luis Pater
5c95129884 Merge branch 'router-for-me:main' into main 2025-12-30 11:48:29 +08:00
hkfires
d443c86620 refactor(config): rename model mapping fields from from/to to name/alias 2025-12-30 11:07:59 +08:00
hkfires
7be3f1c36c refactor(config): rename model-name-mappings to oauth-model-mappings 2025-12-30 11:07:58 +08:00
Luis Pater
50e6d845f4 feat(cliproxy): introduce global model name mappings for improved aliasing and routing 2025-12-30 08:13:06 +08:00
Luis Pater
d35152bbef Merge branch 'router-for-me:main' into main 2025-12-27 22:03:50 +08:00
hkfires
8be06255f7 fix(auth): make provider rotation atomic 2025-12-27 12:56:48 +08:00
Luis Pater
05f249d77f Merge branch 'main' into plus 2025-12-26 12:14:35 +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
Luis Pater
cdb9c2e6e8 Merge remote-tracking branch 'origin/main' into router-for-me/main 2025-12-24 20:18:53 +08:00
hkfires
26fbb77901 refactor(sdk/auth): rename manager.go to conductor.go 2025-12-24 15:21:03 +08:00
Luis Pater
8fee16aecd Merge PR #59: v6.6.50 (resolve conflicts) 2025-12-24 11:06:10 +08:00
hkfires
e76ba0ede9 feat(logging): implement request ID tracking and propagation 2025-12-24 08:32:17 +08:00
Luis Pater
12370ee84e Merge branch 'router-for-me:main' into main 2025-12-22 22:53:29 +08:00
Luis Pater
b84ccc6e7a feat: add unit tests for routing strategies and implement dynamic selector updates
Added comprehensive tests for `FillFirstSelector` and `RoundRobinSelector` to ensure proper behavior, including deterministic, cyclical, and concurrent scenarios. Introduced dynamic routing strategy updates in `service.go`, normalizing strategies and seamlessly switching between `fill-first` and `round-robin`. Updated `Manager` to support selector changes via the new `SetSelector` method.
2025-12-22 22:52:23 +08:00
gwizz
c020fa60d0 fix: keep round-robin as default routing 2025-12-22 23:39:41 +11:00
gwizz
b078be4613 feat: add fill-first routing strategy 2025-12-22 23:38:10 +11:00
Luis Pater
1efade8bdb Merge branch 'main' into plus 2025-12-17 02:50:14 +08:00
Luis Pater
52b6306388 feat(config): add support for model prefixes and prefix normalization
Refactor model management to include an optional `prefix` field for model credentials, enabling better namespace handling. Update affected configuration files, APIs, and handlers to support prefix normalization and routing. Remove unused OpenAI compatibility provider logic to simplify processing.
2025-12-17 01:07:26 +08:00
Luis Pater
bbb21d7c2b Merge branch 'main' into plus 2025-12-15 16:36:11 +08:00
hkfires
f26da24a2f feat(auth): add proxy information to debug logs 2025-12-15 13:14:55 +08:00
Ravens2121
58866b21cb feat: optimize connection pooling and improve Kiro executor reliability
## 中文说明

### 连接池优化
- 为 AMP 代理、SOCKS5 代理和 HTTP 代理配置优化的连接池参数
- MaxIdleConnsPerHost 从默认的 2 增加到 20,支持更多并发用户
- MaxConnsPerHost 设为 0(无限制),避免连接瓶颈
- 添加 IdleConnTimeout (90s) 和其他超时配置

### Kiro 执行器增强
- 添加 Event Stream 消息解析的边界保护,防止越界访问
- 实现实时使用量估算(每 5000 字符或 15 秒发送 ping 事件)
- 正确从上游事件中提取并传递 stop_reason
- 改进输入 token 计算,优先使用 Claude 格式解析
- 添加 max_tokens 截断警告日志

### Token 计算改进
- 添加 tokenizer 缓存(sync.Map)避免重复创建
- 为 Claude/Kiro/AmazonQ 模型添加 1.1 调整因子
- 新增 countClaudeChatTokens 函数支持 Claude API 格式
- 支持图像 token 估算(基于尺寸计算)

### 认证刷新优化
- RefreshLead 从 30 分钟改为 5 分钟,与 Antigravity 保持一致
- 修复 NextRefreshAfter 设置,防止频繁刷新检查
- refreshFailureBackoff 从 5 分钟改为 1 分钟,加快失败恢复

---

## English Description

### Connection Pool Optimization
- Configure optimized connection pool parameters for AMP proxy, SOCKS5 proxy, and HTTP proxy
- Increase MaxIdleConnsPerHost from default 2 to 20 to support more concurrent users
- Set MaxConnsPerHost to 0 (unlimited) to avoid connection bottlenecks
- Add IdleConnTimeout (90s) and other timeout configurations

### Kiro Executor Enhancements
- Add boundary protection for Event Stream message parsing to prevent out-of-bounds access
- Implement real-time usage estimation (send ping events every 5000 chars or 15 seconds)
- Correctly extract and pass stop_reason from upstream events
- Improve input token calculation, prioritize Claude format parsing
- Add max_tokens truncation warning logs

### Token Calculation Improvements
- Add tokenizer cache (sync.Map) to avoid repeated creation
- Add 1.1 adjustment factor for Claude/Kiro/AmazonQ models
- Add countClaudeChatTokens function to support Claude API format
- Support image token estimation (calculated based on dimensions)

### Authentication Refresh Optimization
- Change RefreshLead from 30 minutes to 5 minutes, consistent with Antigravity
- Fix NextRefreshAfter setting to prevent frequent refresh checks
- Change refreshFailureBackoff from 5 minutes to 1 minute for faster failure recovery
2025-12-13 10:21:40 +08:00
Luis Pater
a748e93fd9 **fix(executor, auth): ensure index assignment consistency for auth objects**
- Updated `usage_helpers.go` to call `EnsureIndex()` for proper index assignment in reporter initialization.
- Adjusted `auth/manager.go` to assign auth indices inside a locked section when they are unassigned, ensuring thread safety and consistency.
2025-11-30 16:56:29 +08:00
Luis Pater
bb9955e461 **fix(auth): resolve index reassignment issue during auth management**
- Fixed improper handling of `indexAssigned` and `Index` during auth reassignment.
- Ensured `EnsureIndex` is invoked after validating existing auth entries.
2025-11-24 10:10:09 +08:00
Luis Pater
7063a176f4 #293
**feat(retry): add configurable retry logic with cooldown support**

- Introduced `max-retry-interval` configuration for cooldown durations between retries.
- Added `SetRetryConfig` in `Manager` to handle retry attempts and cooldown intervals.
- Enhanced provider execution logic to include retry attempts, cooldown management, and dynamic wait periods.
- Updated API endpoints and YAML configuration to support `max-retry-interval`.
2025-11-24 09:55:15 +08:00
Luis Pater
db81331ae8 **refactor(middleware): extract request logging logic and optimize condition checks**
- Added `shouldLogRequest` helper to simplify path-based request logging logic.
- Updated middleware to skip management endpoints for improved security.
- Introduced an explicit `nil` logger check for minimal overhead.
- Updated dependencies in `go.mod`.

**feat(auth): add handling for 404 response with retry logic**

- Introduced support for 404 `not_found` status with a 12-hour backoff period.
- Updated `manager.go` to align state and status messages for 404 scenarios.

**refactor(translator): comment out debug logging in Gemini responses request**
2025-11-20 23:20:40 +08:00
Luis Pater
d50b0f7524 **refactor(executor): simplify Gemini CLI execution and remove internal retry logic**
- Removed nested retry handling for 429 rate limit errors.
- Simplified request/response handling by cleaning redundant retry-related code.
- Eliminated `parseRetryDelay` function and max retry configuration logic.
2025-11-20 17:49:37 +08:00
Luis Pater
cc3cf09c00 **feat(auth): add AuthIndex for diagnostics and ensure usage recording** 2025-11-19 22:02:40 +08:00
hkfires
b52a5cc066 feat(auth): add iFlow cookie-based authentication support 2025-11-18 22:35:35 +08:00
Luis Pater
07da781336 feat(registry): add client model support check for executor filtering
- Introduced `ClientSupportsModel` function to `ModelRegistry` for verifying client support for specific models.
- Integrated model support validation into executor candidate filtering logic.
- Updated CLIProxy registry interface to include the new support check method.
2025-10-31 09:15:14 +08:00
hkfires
24446a4dc4 feat(cliproxy): skip persisting runtime-only websocket auths 2025-10-29 21:49:35 +08:00
hkfires
5dced4c0a6 feat(registry): unify Gemini models and add AI Studio set 2025-10-28 19:00:25 +08:00
hkfires
3839d93ba0 feat: add websocket routing and executor unregister API
- Introduce Server.AttachWebsocketRoute(path, handler) to mount websocket
  upgrade handlers on the Gin engine.
- Track registered WS paths via wsRoutes with wsRouteMu to prevent
  duplicate registrations; initialize in NewServer and import sync.
- Add Manager.UnregisterExecutor(provider) for clean executor lifecycle
  management.
- Add github.com/gorilla/websocket v1.5.3 dependency and update go.sum.

Motivation: enable services to expose WS endpoints through the core server
and allow removing auth executors dynamically while avoiding duplicate
route setup. No breaking changes.
2025-10-26 07:46:03 +08:00
Luis Pater
d225558dae feat: improve error handling with added status codes and headers
- Updated Execute methods to include enhanced error handling via `StatusCode` and `Headers` extraction.
- Introduced structured error responses for cooling down scenarios, providing additional metadata and retry suggestions.
- Refined quota management, allowing for differentiation between cool-down, disabled, and other block reasons.
- Improved model filtering logic based on client availability and suspension criteria.
2025-10-22 09:01:11 +08:00
Luis Pater
9678be7aa4 feat: add DisableCooling configuration to manage quota cooldown behavior 2025-10-21 21:51:30 +08:00
Luis Pater
3569e5779a feat: enhance quota management with backoff levels and cooldown logic 2025-10-21 18:44:28 +08:00
hkfires
c3f88126e6 refactor(provider): remove Gemini Web cookie-based support 2025-10-11 12:56:07 +08:00
hkfires
b895018ff5 refactor(provider): remove Gemini Web cookie-based provider 2025-10-11 12:53:03 +08:00
Luis Pater
829dd06b42 feat(cliproxy/auth): restructure auth candidate selection and ensure synchronization
- Refactored candidate selection logic in `auth/manager.go`.
- Ensured proper synchronization around `mu.RUnlock` to prevent racing conditions.
2025-10-10 02:35:15 +08:00
hkfires
1d70336a91 fix(gemini-web): Correct ambiguity check in conversation lookup 2025-09-30 12:21:51 +08:00
hkfires
6080527e9e feat(gemini-web): Namespace conversation index by account label 2025-09-30 12:21:51 +08:00
hkfires
82187bffba feat(gemini-web): Add conversation affinity selector 2025-09-30 12:21:51 +08:00
Luis Pater
d01c4904ff refactor(auth): replace TokenRecord with coreauth.Auth and migrate TokenStore to coreauth.Store
- Replaced `TokenRecord` with `coreauth.Auth` for centralized and consistent authentication data structures.
- Migrated `TokenStore` interface to `coreauth.Store` for alignment with core CLIProxy authentication.
- Updated related login methods, token persistence logic, and file storage handling to use the new `coreauth.Auth` model.
2025-09-29 09:31:21 +08:00
hkfires
9b80820b17 refactor(auth): Move candidate sorting to RoundRobinSelector 2025-09-26 10:50:15 +08:00
hkfires
e836b4ac10 fix(auth): Make round-robin auth selection deterministic 2025-09-26 09:49:53 +08:00