86 Commits

• fix(watcher): improve client reload logic and prevent redundant updates

  - replace debounce timing with content-based change detection using SHA256 hashes
  - skip client reload when auth file content is unchanged
  - handle empty auth files gracefully by ignoring them
  - ensure hash cache is updated only on successful client creation
  - clean up hash cache when clients are removed

  hkfires · 2025-09-05 13:53:15 +08:00
  57484b97bb
• refactor(watcher): restructure client management and API key handling

  - separate file-based and API key-based clients in watcher
  - improve client reloading logic with better locking and error handling
  - add dedicated functions for building API key clients and loading file clients
  - update combined client map generation to include cached API key clients
  - enhance logging and debugging information during client reloads
  - fix potential race conditions in client updates and removals

  hkfires · 2025-09-05 13:25:30 +08:00
  0e0602c553
• Add FunctionCallIndex to ConvertCliToOpenAIParams and enhance tool call handling

  - Introduced `FunctionCallIndex` to track and manage function call indices within `ConvertCliToOpenAIParams`.
  - Enhanced handling for `response.completed` and `response.output_item.done` data types to support tool call scenarios.
  - Improved logic for restoring original tool names and setting function arguments during response parsing.

  Luis Pater · 2025-09-05 09:02:24 +08:00
  54ffb52838
• Add Gemini 2.5 Flash-Lite Model
  hkfires · 2025-09-04 11:59:48 +08:00
  3e09bc9470
• Add debounce logic for file events to prevent duplicate reloads
  hkfires · 2025-09-04 10:28:54 +08:00
  5ed79e5aa3
• Add reasoning/thinking configuration handling for Claude and OpenAI translators

  - Implemented `thinkingConfig` handling to allow reasoning effort configuration in request generation.
  - Added support for reasoning content deltas (`thinking_delta`) in response processing.
  - Enhanced reasoning-related token budget mappings for various reasoning levels.
  - Improved response handling logic to ensure proper reasoning content inclusion.

  Luis Pater · 2025-09-04 09:43:22 +08:00
  f1d6f01585
• Replace path with filepath for cross-platform compatibility

  - Updated imports and function calls to use `filepath` across all token storage implementations and server entry point.
  - Ensured consistent handling of directory and file paths for improved portability.

  Luis Pater · 2025-09-04 08:23:51 +08:00
  d4709ffcf9
• Add reverse mappings for original tool names and improve error logging

  - Introduced reverse mapping logic for tool names in translators to restore original names when shortened.
  - Enhanced error handling by logging API response errors consistently across handlers.
  - Refactored request and response loggers to include API error details, improving debugging capabilities.
  - Integrated robust tool name shortening and uniqueness mechanisms for OpenAI, Gemini, and Claude requests.
  - Improved handler retry logic to properly capture and respond to errors.

  Luis Pater · 2025-09-04 02:39:56 +08:00
  ad943b2d4d
• Refactor client map construction to include all client types and enhance callback updates

  - Added `buildCombinedClientMap` to merge file-based clients with API key and compatibility clients.
  - Updated callbacks to use the combined client map for consistency.
  - Improved error logging and variable naming for clarity in client creation logic.

  Luis Pater · 2025-09-03 22:26:07 +08:00
  7209fa233f
• Refactor cliCancel calls to remove unused resp argument across handlers.
  Luis Pater · 2025-09-03 21:13:22 +08:00
  70e916942e
• feat(watcher): implement incremental client hot-reloading
  hkfires · 2025-09-03 20:47:43 +08:00
  f60ef0b2e7
• Enhance parseArgsToMap with tolerant JSON parsing

  - Introduced `tolerantParseJSONMap` to handle bareword values in streamed tool calls.
  - Added robust handling for JSON strings, objects, arrays, and numerical values.
  - Improved fallback mechanisms to ensure reliable parsing.

  Luis Pater · 2025-09-03 16:11:26 +08:00
  6d2f7e3ce0
• Add support for Codex API key authentication

  - Introduced functionality to handle Codex API keys, including initialization and management via new endpoints in the management API.
  - Updated Codex client to support both OAuth and API key authentication.
  - Documented Codex API key configuration in both English and Chinese README files.
  - Enhanced logging to distinguish between API key and OAuth usage scenarios.

  Luis Pater · 2025-09-03 03:36:56 +08:00
  c4a42eb1f0
• Remove commented debug logging in ConvertOpenAIResponsesRequestToGeminiCLI
  Luis Pater · 2025-09-03 03:03:07 +08:00
  b6f8677b01
• Add Codex load balancing documentation and refine JSON handling logic

  - Updated README and README_CN to include a guide for configuring multiple account load balancing with CLI Proxy API.
  - Enhanced JSON handling in gemini translators by differentiating object and string outputs.
  - Added commented debug logging for Gemini CLI response conversion.

  Luis Pater · 2025-09-03 01:33:26 +08:00
  67e0b71c18
• Remove redundant dataUglyTag parsing logic in streaming responses

  Eliminated duplicate blocks handling `dataUglyTag` in `openai-compatibility_client.go`, simplifying the streaming response logic.

  Luis Pater · 2025-09-03 00:44:35 +08:00
  b0f72736b0
• Extract argument parsing logic into parseArgsToMap helper function

  Simplifies parsing and error handling for function arguments across OpenAI response processing methods. Replaces repeated logic with a reusable utility function.

  Luis Pater · 2025-09-03 00:41:16 +08:00
  ae06f13e0e
• Merge branch 'main' of github.com:luispater/CLIProxyAPI
  Luis Pater · 2025-09-03 00:16:04 +08:00
  edf9d9b747
• Add OpenAI Responses support
  Luis Pater · 2025-09-03 00:15:35 +08:00
  3acdec51bd
• Add OpenAI Responses support
  Luis Pater · 2025-09-03 00:09:23 +08:00
  ce5d2bad97
• **Fix model switch logic when quota is exceeded**

  Ensure `modelName` is updated after switching to a new model, avoiding inconsistencies in subsequent iterations.

  Luis Pater · 2025-09-01 21:37:03 +08:00
  34855bc647
• **Handle data: without trailing space in streaming responses**

  Add support for API providers that emit `data:` (no space) in Server‑Sent Events. Introduces a new `dataUglyTag` and corresponding parsing logic to correctly process and forward these lines, ensuring compatibility with non‑standard streaming formats.
  
  Fuck for them all

  Luis Pater · 2025-09-01 17:38:24 +08:00
  56c8297f6b
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 11:00:47 +08:00
  e11637dc62
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 10:28:29 +08:00
  e0bff9f212
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 10:20:50 +08:00
  bff6f6679b
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 10:07:33 +08:00
  305916f5a9
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 08:37:41 +08:00
  1f46dc2715
• Refactor translator packages for OpenAI Chat Completions

  - Renamed `openai` packages to `chat_completions` across translator modules.
  - Introduced `openai_responses_handlers` with handlers for `/v1/models` and OpenAI-compatible chat completions endpoints.
  - Updated constants and registry identifiers for OpenAI response type.
  - Simplified request/response conversions and added detailed retry/error handling.
  - Added `golang.org/x/crypto` for additional cryptographic functions.

  Luis Pater · 2025-09-01 08:18:59 +08:00
  e3994ace33
• Update PassthroughGeminiResponseStream to handle [DONE] marker

  - Added logic to return an empty slice when the raw JSON equals the `[DONE]` marker.
  - Ensures proper termination of streamed Gemini responses.

  Luis Pater · 2025-09-01 02:00:55 +08:00
  bdac24bb4e
• Add Gemini-to-Gemini request normalization and passthrough support

  - Introduced a `ConvertGeminiRequestToGemini` function to normalize Gemini v1beta requests by ensuring valid or default roles.
  - Added passthrough response handlers for both streamed and non-streamed Gemini responses.
  - Registered translators for Gemini-to-Gemini traffic in the initialization process.
  - Updated `gemini-cli` request normalization to align with the new Gemini translator logic.

  Luis Pater · 2025-08-31 15:05:16 +08:00
  c0eaa41c7a
• Add management API handlers for config and auth file management

  - Implemented CRUD operations for authentication files.
  - Added endpoints for managing API keys, quotas, proxy settings, and other configurations.
  - Enhanced management access with robust validation, remote access control, and persistence support.
  - Updated README with new configuration details.
  
  Fixed OpenAI Chat Completions for codex

  Luis Pater · 2025-08-31 14:29:23 +08:00
  db43930b98
• Enhance client reload process with new OpenAI compatibility support

  - Added handling for OpenAI-compatible providers during client reload.
  - Implemented client unregistration for old clients during reload.
  - Improved logging for detailed client reload insights.
  
  Expand `AuthDir` handling to support tilde (`~`) for home directory resolution
  
  - Added logic to replace `~` with the user's home directory in `AuthDir`.
  - Prevents errors when using `~` in configuration paths.

  Luis Pater · 2025-08-31 03:04:46 +08:00
  b1254106ee
• Add support for new GPT-5 model variants

  - Renamed existing GPT-5 variants for consistency (`nano` → `minimal`, `mini` → `low`, etc.).
  - Added metadata definitions for new variants: `gpt-5-minimal`, `gpt-5-low`, `gpt-5-medium`, and updated logic to reflect variant-specific reasoning efforts.

  Luis Pater · 2025-08-30 22:00:37 +08:00
  9c9ea99380
• Add token refresh handling for 401 responses across clients

  - Implemented `RefreshTokens` method in client interfaces and Gemini clients.
  - Updated handlers to call `RefreshTokens` on 401 responses and retry requests if token refresh succeeds.
  - Enhanced error handling and retry logic to accommodate token refresh flow.
  
  Update README to include Qwen login instructions
  
  - Added Qwen OAuth login command instructions in both English and Chinese README files.
  - Made minor updates to existing command examples for consistency.

  Luis Pater · 2025-08-30 17:26:41 +08:00
  0331660fe2
• Add token refresh handling for 401 responses across clients

  - Implemented `RefreshTokens` method in client interfaces and Gemini clients.
  - Updated handlers to call `RefreshTokens` on 401 responses and retry requests if token refresh succeeds.
  - Enhanced error handling and retry logic to accommodate token refresh flow.

  Luis Pater · 2025-08-30 16:10:56 +08:00
  512c8b600a
• Update README documentation to clarify auth-dir configuration for Windows users

  - Added a note for setting `auth-dir` on Windows systems in both English and Chinese README files.
  - Improved descriptions for existing configuration options.
  
  Address Qwen3 tool injection issue to prevent random token insertions
  
  - Modify Qwen client to insert a placeholder tool when none is defined, avoiding erratic behavior in streaming responses.

  Luis Pater · 2025-08-29 17:28:55 +08:00
  f1d9364ef4
• Unlock mutex before returning error in handlers.go to prevent deadlocks
  Luis Pater · 2025-08-29 09:46:12 +08:00
  09b9d3b3fa
• Fix some bugs.
  Luis Pater · 2025-08-29 04:05:08 +08:00
  e9e0016a63
• Add nil-check for GetRequestMutex across handlers to prevent potential panics

  - Updated all handlers to safely unlock the request mutex only if it's non-nil.
  - Enhanced mutex locking and unlocking logic to avoid runtime errors.
  - Improved robustness of resource cleanup across clients.
  
  Add `GetRequestMutex` method for synchronization across clients
  
  - Introduced a new `GetRequestMutex` method in OpenAICompatibilityClient, CodexClient, GeminiCLIClient, GeminiClient, and QwenClient for request synchronization.
  - Ensures only one request is processed at a time to manage quotas effectively.

  Luis Pater · 2025-08-29 00:23:37 +08:00
  3704dae342
• Add /v1/completions endpoint with OpenAI compatibility

  - Implemented `/v1/completions` endpoint mirroring OpenAI's completions API specification.
  - Added conversion functions to translate between completions and chat completions formats.
  - Introduced streaming and non-streaming response handling for completions requests.
  - Updated `server.go` to register the new endpoint and include it in the API's metadata.

  Luis Pater · 2025-08-28 00:30:46 +08:00
  bea5f97cbf
• Suppress debug logs for model routing and ignore empty tools arrays

  - Comment out verbose routing logs in the API server to reduce noise.
  - Remove the `tools` field from Qwen client requests when it is an empty array.
  - Add guards in Claude, Codex, Gemini‑CLI, and Gemini translators to skip tool conversion when the `tools` array is empty, preventing unnecessary payload modifications.

  Luis Pater · 2025-08-27 22:29:08 +08:00
  7a6adfa97e
• Add support for localhost unauthenticated requests

  - Introduced `AllowLocalhostUnauthenticated` flag allowing unauthenticated requests from localhost.
  - Updated authentication middleware to bypass checks for localhost when enabled.
  
  Add new Gemini CLI models and update model registry function
  
  - Introduced `GetGeminiCLIModels` for updated Gemini CLI model definitions.
  - Added new models: "Gemini 2.5 Flash Lite" and "Gemini 2.5 Pro".
  - Updated `RegisterModels` to use `GetGeminiCLIModels` in Gemini client initialization.

  Luis Pater · 2025-08-27 21:20:25 +08:00
  1c4183d943
• Improved the /v1/models endpoint
  Luis Pater · 2025-08-27 21:01:37 +08:00
  dff31a7a4c
• Add OpenAI compatibility support and improve resource cleanup

  - Introduced OpenAI compatibility configurations for external providers, enabling model alias routing via the OpenAI API format.
  - Enhanced provider logic in `GetProviderName` to handle OpenAI aliases and added new helper functions for compatibility checks.
  - Updated API handlers and client initialization to support OpenAI compatibility models.
  - Improved resource cleanup across clients by closing response bodies and streams using deferred functions.

  Luis Pater · 2025-08-26 03:33:46 +08:00
  ed8873fbb0
• Refactor API handlers to implement retry mechanism with configurable limits and improved error handling

  - Introduced retry counter with a configurable ` RequestRetry ` limit in all handlers.
  - Enhanced error handling with specific HTTP status codes for switching clients.
  - Standardized response forwarding for non-retriable errors.
  - Improved logging for quota and client switch scenarios.

  Luis Pater · 2025-08-25 23:43:49 +08:00
  9102ff031d
• Refactor codebase
  Luis Pater · 2025-08-25 16:58:16 +08:00
  8c555c4e69
• Add Qwen support
  Luis Pater · 2025-08-21 15:22:53 +08:00
  aa2f37d54d
• Add claude code support
  Luis Pater · 2025-08-21 02:53:28 +08:00
  d58cc55cb2
• Refactor error handling and variable declarations in browser and logging modules

  - Simplified variable initialization in `browser.go` for readability.
  - Updated error handling in `request_logger.go` with better resource cleanup using deferred anonymous functions.
  
  Refactor API handlers to use `GetContextWithCancel` for streamlined context creation and response handling
  
  - Replaced redundant `context.WithCancel` and `context.WithValue` logic with the new `GetContextWithCancel` utility in all handlers.
  - Centralized API response storage in the given context during cancellation.
  - Updated associated cancellation calls for consistency and improved resource management.
  
  - Replaced `apiResponseData` with `AddAPIResponseData` for centralized response recording.
  - Simplified cancellation logic by switching to a boolean-based `cliCancel` method.
  - Removed unused `apiResponseData` slices across handlers to reduce memory usage.
  - Updated `handlers.go` to support unified response data storage per request context.

  Luis Pater · 2025-08-17 20:13:45 +08:00
  c5cc238308
• Refactor Gemini API handlers to standardize response field names and improve model descriptions
  Luis Pater · 2025-08-17 00:28:13 +08:00
  6bbdf67f96