Calcium-Ion
b28ac71722
Merge pull request #2703 from seefs001/feature/log-conversion-info
...
feat: log shows request conversion
2026-01-21 23:48:08 +08:00
Seefs
6582020c80
feat: optimized display
2026-01-21 00:01:36 +08:00
Seefs
d4582ede98
feat: log shows request conversion
2026-01-20 23:43:29 +08:00
Seefs
af2d6ad8d2
feat: TLS_INSECURE_SKIP_VERIFY env
2026-01-15 14:43:53 +08:00
Seefs
e5cb9ac03a
feat: codex channel ( #2652 )
...
* feat: codex channel
* feat: codex channel
* feat: codex oauth flow
* feat: codex refresh cred
* feat: codex usage
* fix: codex err message detail
* fix: codex setting ui
* feat: codex refresh cred task
* fix: import err
* fix: codex store must be false
* fix: chat -> responses tool call
* fix: chat -> responses tool call
2026-01-14 22:29:43 +08:00
Seefs
41da848c56
Merge pull request #2647 from seefs001/feature/status-code-auto-disable
...
feat: status code auto-disable configuration
2026-01-12 18:47:45 +08:00
Seefs
62b796fa6a
feat: /v1/chat/completion -> /v1/response ( #2629 )
...
* feat: /v1/chat/completion -> /v1/response
2026-01-11 21:38:07 +08:00
Seefs
5f37a1e97c
fix: fix the proxyURL is empty, not using the default HTTP client configuration && the AWS calling side did not apply the relay timeout.
2026-01-05 17:56:24 +08:00
Calcium-Ion
e8aaed440c
Merge pull request #2558 from seefs001/fix/gemini-tool-call
...
fix: gemini request -> openai tool call
2026-01-03 12:37:28 +08:00
Seefs
f1ba624df2
Merge pull request #2547 from wwalt1a/feat/support-proxy-env-vars
2026-01-03 09:35:51 +08:00
Seefs
ddb40b1a6e
fix: gemini request -> openai tool call
2025-12-31 18:09:21 +08:00
feitianbubu
d474ed4778
feat: flush response writer after copying body
2025-12-30 17:52:57 +08:00
wwalt1a
04ea79c429
feat: support HTTP_PROXY environment variable for default HTTP client
...
- Add Proxy: http.ProxyFromEnvironment to default transport
- Allow users to set global proxy via Docker environment variables
- Per-channel proxy settings still override global proxy
- Fully backward compatible
2025-12-30 03:55:06 +08:00
Seefs
58db72d459
fix: Fix Openrouter test errors and optimize error messages ( #2433 )
...
* fix: Refine openrouter error
* fix: Refine openrouter error
* fix: openrouter test max_output_token
* fix: optimize messages
* fix: maxToken unified to 16
* fix: codex系列模型使用 responses接口
* fix: codex系列模型使用 responses接口
* fix: 状态码非200打印错误信息
* fix: 日志里没有报错的响应体
2025-12-26 13:58:44 +08:00
Calcium-Ion
88e394a976
Merge pull request #2513 from seefs001/fix/token-auth-bearer
...
fix: 支持小写bearer和Bearer后带多个空格 && 修复 WSS预扣费错误提取key的问题
2025-12-26 13:51:32 +08:00
t0ng7u
83fbaba768
🚀 fix(model-sync): avoid unnecessary upstream fetch while keeping overwrite updates working
...
- Only short-circuit when there are no missing models AND no overwrite fields requested
- Preserve overwrite behavior even when the missing-model list is empty
- Always return empty arrays (not null) for list fields to keep API responses stable
- Clarify SyncUpstreamModels behavior in comments (create missing models + optional overwrite updates)
2025-12-25 23:01:09 +08:00
Seefs
14c58aea77
fix: 支持小写bearer和Bearer后带多个空格 && 修复 WSS预扣费错误提取key的问题
2025-12-24 15:52:56 +08:00
Jerry
31a79620ba
Resolving event mismatch in OpenAI2Claude
...
add stricter validation for content_block_start corresponding to
tool call
and fix the crash issue when Claude Code is processing tool call
2025-12-24 14:52:39 +08:00
CaIon
a2da6a9e90
refactor(channel_select): improve retry logic with reset functionality
2025-12-13 18:09:10 +08:00
CaIon
21fca238bf
refactor(error): replace dto.OpenAIError with types.OpenAIError for consistency
2025-12-13 16:43:57 +08:00
CaIon
c51936e068
refactor(channel_select): enhance retry logic and context key usage for channel selection
2025-12-13 16:43:38 +08:00
CaIon
b523f6a0ba
fix(channel_select): adjust priority retry logic for cross-group channel selection
2025-12-13 01:04:10 +08:00
CaIon
ce6fb95f96
refactor(relay): update channel retrieval to use RelayInfo structure
2025-12-12 22:04:38 +08:00
Calcium-Ion
147659fb6e
Merge pull request #2426 from QuantumNous/feat/auto-cross-group-retry
...
feat(token): add cross-group retry option for token processing
2025-12-12 20:45:54 +08:00
CaIon
7e1d1350c7
feat: implement cross-group retry functionality and update translations
2025-12-12 18:28:33 +08:00
CaIon
01b4039e96
feat(token): add cross-group retry option for token processing
2025-12-12 17:59:21 +08:00
Calcium-Ion
fca015c6c4
Merge pull request #2397 from seefs001/fix/tool-call-claude
...
fix: try to fix tool call issues
2025-12-09 16:57:24 +08:00
Seefs
1cb2b6f882
fix:try to fix tool call issues
2025-12-09 13:55:52 +08:00
Seefs
5889571108
fix: Use channel proxy settings for task query scenarios
2025-12-09 11:15:27 +08:00
CaIon
7d1bad1b37
fix(token_counter): correct model name reference in image token estimation
2025-12-03 00:25:05 +08:00
Calcium-Ion
48635360cd
Merge pull request #2355 from QuantumNous/feat/optimize-token-counter
...
feat: refactor token estimation logic
2025-12-02 21:51:09 +08:00
CaIon
0c051e968f
feat(token_estimator): add concurrency support for multipliers retrieval
2025-12-02 21:38:58 +08:00
CaIon
f5b409d74f
feat: refactor token estimation logic
...
- Introduced new OpenAI text models in `common/model.go`.
- Added `IsOpenAITextModel` function to check for OpenAI text models.
- Refactored token estimation methods across various channels to use estimated prompt tokens instead of direct prompt token counts.
- Updated related functions and structures to accommodate the new token estimation approach, enhancing overall token management.
2025-12-02 21:34:39 +08:00
Papersnake
2f7eebcd10
fix: add ForceAttemptHTTP2
2025-12-02 10:08:58 +08:00
Papersnake
3954feb993
fix: set MaxIdleConnsPerHost to 100
2025-12-02 09:55:03 +08:00
CaIon
0952973887
feat: Add CountToken configuration and update token counting logic
2025-11-22 17:15:34 +08:00
CaIon
84745d5ca4
feat: Add ContextKeyLocalCountTokens and update ResponseText2Usage to use context in multiple channels
2025-11-21 18:17:01 +08:00
Seefs
df2ee649ab
feat: claude 1h cache ( #2155 )
...
* feat: claude 1h cache
* feat: claude 1h cache
* fix price
2025-11-04 00:20:50 +08:00
Seefs
8f862152e8
Merge pull request #2124 from feitianbubu/pr/fix-topup-link
...
fix: correct topUp link
2025-10-31 13:43:23 +08:00
CaIon
52d9b8cc78
refactor(group): update user group handling to utilize userUsableGroups directly and add GetUserGroupRatio function
2025-10-30 21:16:42 +08:00
Seefs
1f419a3c71
Merge pull request #2121 from QuantumNous/feat/special_group
...
feat: add special user usable group setting
2025-10-29 18:54:51 +09:00
feitianbubu
74e5e640c5
fix: correct topUp link
2025-10-29 16:55:29 +08:00
CaIon
1ded19795a
feat: add special user usable group setting
2025-10-28 23:25:43 +08:00
CaIon
2b70095b47
feat: implement audio duration retrieval without ffmpeg dependencies
2025-10-28 15:50:45 +08:00
Seefs
86c63ea4a7
feat: endpoint type log
2025-10-13 22:44:54 +08:00
Seefs
2624c48113
feat: endpoint type log
2025-10-13 22:25:39 +08:00
yanggh
8b9188c584
fix(convert): 修复 OpenAI 转 Claude 流时 thinking 块的格式问题
...
将 `ClaudeMediaMessage.Thinking` 的类型从 `string` 修改为 `*string`，以解决 `omitempty` 导致 `"thinking": ""` 字段在 JSON 序列化时被忽略的问题。
同时更新了 `service/convert.go` 和 `relay/channel/claude/relay-claude.go` 中的相关逻辑，以兼容新的指针类型，确保生成的 Claude 事件流符合官方规范。
2025-10-13 19:32:17 +08:00
CaIon
c13bb67360
fix: mask sensitive information in error messages and refine task retrieval query
2025-10-12 12:25:11 +08:00
Seefs
e1c7a4f41f
format: package name -> github.com/QuantumNous/new-api ( #2017 )
2025-10-11 15:30:09 +08:00
Seefs
76ab8a480a
Merge pull request #1401 from feitianbubu/pr/add-qwen-channel-auto-disabled
...
feat: add qwen channel auto disabled
2025-10-10 16:41:43 +08:00
