RedwindA c2464fc877 fix(gemini): fetch model list via native v1beta/models endpoint ...

Use the native Gemini Models API (/v1beta/models) instead of the OpenAI-compatible
path when listing models for Gemini channels, improving compatibility with
third-party Gemini-format providers that don't implement OpenAI routes.

- Add paginated model listing with timeout and optional proxy support
- Select an enabled key for multi-key Gemini channels

2026-01-09 18:00:40 +08:00

..

channel

fix(gemini): fetch model list via native v1beta/models endpoint

2026-01-09 18:00:40 +08:00

common

feat: add parameter coverage for the operations: copy, trim_prefix, trim_suffix, ensure_prefix, ensure_suffix, trim_space, to_lower, to_upper, replace, and regex_replace

2026-01-03 10:27:16 +08:00

common_handler

feat: refactor token estimation logic

2025-12-02 21:34:39 +08:00

constant

feat: add support for Midjourney relay mode based on path prefix

2025-08-16 18:26:26 +08:00

helper

fix(helper): improve error handling in FlushWriter and related functions

2025-12-13 13:29:21 +08:00

audio_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

claude_handler.go

feat: embedding param override && internal params

2025-11-22 18:27:17 +08:00

compatible_handler.go

feat(ratio): add functions to check for audio ratios and clean up unused code

2025-12-31 21:29:10 +08:00

embedding_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

gemini_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

image_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

mjproxy_handler.go

feat: endpoint type log

2025-10-13 22:25:39 +08:00

relay_adaptor.go

feat: add MiniMax Hailuo video

2025-11-14 11:55:43 +08:00

relay_task.go

fix(task): 修复使用 auto 分组时 Task Relay 不记录日志和不扣费的问题

2026-01-06 00:16:50 +08:00

rerank_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

responses_handler.go

feat(adaptor): 新适配百炼多种图片生成模型

2025-12-29 23:00:17 +08:00

websocket.go

format: package name -> github.com/QuantumNous/new-api (#2017)

2025-10-11 15:30:09 +08:00