18 Commits

• Merge pull request #58 from router-for-me/v6-test

  refactor(gemini-web): Remove auto-refresh, auto-close, and caching

  Luis Pater · 2025-09-23 18:20:47 +08:00
  c159180589
• refactor(gemini-web): Remove auto-refresh, auto-close, and caching

  This commit simplifies the Gemini web client by removing several complex, stateful features. The previous implementation for auto-refreshing cookies and auto-closing the client involved background goroutines, timers, and file system caching, which made the client's lifecycle difficult to manage.
  
  The following features have been removed:
  - The cookie auto-refresh mechanism, including the background goroutine (`rotateCookies`) and related configuration fields.
  - The file-based caching for the `__Secure-1PSIDTS` token. The `rotate1PSIDTS` function now fetches a new token on every call.
  - The auto-close functionality, which used timers to close the client after a period of inactivity.
  - Associated configuration options and methods (`WithAccountLabel`, `WithOnCookiesRefreshed`, `Close`, etc.).
  
  By removing this logic, the client becomes more stateless and predictable. The responsibility for managing the client's lifecycle and handling token expiration is now shifted to the caller, leading to a simpler and more robust integration.

  hkfires · 2025-09-23 12:48:30 +08:00
  8e485e5868
• feat(claude-executor): add ZSTD decoding support for Claude executor responses

  - Integrated ZSTD decompression via `github.com/klauspost/compress` for responses with "zstd" content-encoding.
  - Added helper `hasZSTDEcoding` to detect ZSTD-encoded responses.
  - Updated response handling logic to initialize and use a ZSTD decoder when necessary.
  
  refactor(api-handlers): split streaming and non-streaming response handling
  
  - Introduced `handleNonStreamingResponse` for processing non-streaming requests in `ClaudeCodeAPIHandler`.
  - Improved code clarity by separating streaming and non-streaming logic.
  
  fix(service): remove redundant token refresh interval assignment logic in `cliproxy` service.

  Luis Pater · 2025-09-23 12:44:44 +08:00
  11b0efc38f
• feat(gemini-web): Inject fallback text for image-only flash model responses
  hkfires · 2025-09-23 10:05:59 +08:00
  50c8f7f96f
• feat(gemini-executor): implement CountTokens method with request translation and API integration

  - Added `CountTokens` for token counting requests in Gemini executor.
  - Integrated request translation via `sdktranslator` and response handling.
  - Improved error handling, logging, and API request configuration with headers.

  Luis Pater · 2025-09-23 02:45:08 +08:00
  e313d39be8
• feat(executor): add CountTokens support across all executors

  - Introduced `CountTokens` method to Codex, Claude, Gemini, Qwen, OpenAI-compatible, and other executors.
  - Implemented `ExecuteCount` in `AuthManager` for token counting via provider round-robin.
  - Updated handlers to leverage `ExecuteCountWithAuthManager` for streamlined token counting.
  - Added fallback and error handling logic for token counting requests.

  Luis Pater · 2025-09-23 02:27:51 +08:00
  ac59023abb
• refactor(headers): centralize header logic using EnsureHeader utility

  - Introduced `EnsureHeader` in `internal/misc/header_utils.go` to streamline header setting across executors.
  - Updated Codex, Claude, and Gemini executors to utilize `EnsureHeader` for consistent header application.
  - Incorporated Gin context headers (if available) into request header manipulation for better integration.

  Luis Pater · 2025-09-23 02:01:57 +08:00
  d32fc0400e
• refactor(executor): centralize header application logic for executors

  - Replaced repetitive header setting logic with helper methods (`applyCodexHeaders`, `applyClaudeHeaders`, `applyQwenHeaders`) in Codex, Claude, and Qwen executors.
  - Ensured consistent headers in HTTP requests across all executors.
  - Introduced UUID and additional structured headers for better traceability (e.g., session IDs, metadata).

  Luis Pater · 2025-09-23 01:20:10 +08:00
  7ea88358f0
• chore(executor): add debug logging for API request errors

  - Added detailed debug logs in all executors (Codex, Claude, Gemini, Qwen, OpenAI-compatible) to capture HTTP status and response body for failed API requests.

  Luis Pater · 2025-09-22 23:37:53 +08:00
  c6b391304d
• feat(auth): standardize last_refresh metadata handling across executors

  - Added `last_refresh` timestamp to metadata for Codex, Claude, Qwen, and Gemini executors.
  - Implemented `extractLastRefreshTimestamp` utility for parsing diverse timestamp formats in management handlers.
  - Ensured consistent update and preservation of `last_refresh` in file-based auth handling.

  Luis Pater · 2025-09-22 23:23:31 +08:00
  2e836cee88
• feat(openai-compat): enhance provider key handling and model resolution

  - Introduced dynamic `providerKey` resolution for OpenAI-compatible providers, incorporating attributes like `provider_key` and `compat_name`.
  - Implemented upstream model overrides via `resolveUpstreamModel` and `overrideModel` methods in the OpenAI executor.
  - Updated registry logic to correctly store provider mappings and register clients using normalized keys.
  - Ensured consistency in handling empty or default provider names across components.

  Luis Pater · 2025-09-22 22:54:21 +08:00
  e41d127732
• feat(gemini-web): Implement proactive PSIDTS cookie rotation
  hkfires · 2025-09-22 21:54:52 +08:00
  22a69333a0
• refactor(auth): remove unused Refresh methods from authenticators

  - Deleted `Refresh` implementations in Codex, Claude, Gemini, Qwen, and Gemini-web authenticators.
  - Updated the `Authenticator` interface to exclude `Refresh` for cleaner design.
  - Revised `Manager` and related components to handle refresh logic improvements.
  - Simplified token refresh behavior and eliminated redundant code paths.

  Luis Pater · 2025-09-22 21:11:53 +08:00
  053134f66e
• chore(logging): add debug logs for executor Refresh methods

  - Introduced `logrus` for structured debugging across all executors.
  - Added debug log messages in `Refresh` methods for better traceability.
  - Updated `Manager` to log additional details during refresh checks.

  Luis Pater · 2025-09-22 20:03:31 +08:00
  837ae1b1b3
• feat: implement token refresh support for executors

  - Added `Refresh` method implementations for Codex, Claude, Gemini, and Qwen executors.
  - Introduced OAuth-based token handling for Gemini and Qwen with support for refresh tokens.
  - Updated Codex and Claude to use new internal auth services.
  - Enhanced metadata structure and consistency for token storage across all executors.

  Luis Pater · 2025-09-22 09:27:03 +08:00
  0607e52767
• feat: enhance request logging and account handling in CLI proxy

  - Added helper functions to log API request and response payloads in the Gin context.
  - Improved `AccountInfo` to support cookie-based authentication in addition to API key and OAuth.
  - Updated log messages for better clarity on account types used.

  Luis Pater · 2025-09-22 03:09:15 +08:00
  d5ad5fab87
• refactor: standardize constant naming and improve file-based auth handling

  - Renamed constants from uppercase to CamelCase for consistency.
  - Replaced redundant file-based auth handling logic with the new `util.CountAuthFiles` helper.
  - Fixed various error-handling inconsistencies and enhanced robustness in file operations.
  - Streamlined auth client reload logic in server and watcher components.
  - Applied minor code readability improvements across multiple packages.

  Luis Pater · 2025-09-22 02:56:45 +08:00
  d9ad65622a
• v6 version first commit
  Luis Pater · 2025-09-22 01:40:24 +08:00
  4999fce7f4