What's Changed

• feat: map OpenAI developer role to Gemini system instructions by @RedwindA in #2536
• feat: ionet integrate by @seefs001 in #2105
• feat: Add "wan2.6-i2v" video ratio configuration to Ali adaptor. by @seefs001 in #2544
• fix: glm 4.7 finish reason by @seefs001 in #2545
• feat: flush response writer after copying body by @feitianbubu in #2551
• feat(checkin): add check-in functionality by @Calcium-Ion in #2565
• fix(checkin): prevent visual flicker when loading check-in component by @RedwindA in #2566
• remove duplicate condition in TaskLogsColumnDefs by @zpc7 in #2554
• feat: 支持仅使用x-api-key获取anthropic格式的模型列表 #2422 by @atopos31 in #2425
• feat: support HTTP_PROXY environment variable for default HTTP client by @wwalt1a in #2547
• fix: kling correct fail reason by @feitianbubu in #2532
• feat: support claude-haiku-4-5-20251001 on vertex by @prnake in #2393
• fix(task): 修复渠道配置多个key时无法获取任务的问题 by @a4399518s in #2447
• fix: CrossGroupRetry default false by @feitianbubu in #2570
• feat: add support for Doubao /v1/responses by @seefs001 in #2567
• feat: check-in feature integrates Turnstile security check by @seefs001 in #2571
• fix: gemini request -> openai tool call by @seefs001 in #2558
• fix: fix model deployment style issues, lint problems, and i18n gaps. by @seefs001 in #2556
• feat: add parameter coverage for more operations by @seefs001 in #2568
• fix: 修复智普、Moonshot渠道在stream=true时无法拿到cacheTokens的统计数据。 by @shikaiwei1 in #2550
• fix: 修复 gemini 文件类型不支持 image/jpg by @xyfacai in #2578
• fix: fix the proxyURL is empty, not using the default HTTP client configuration && the AWS calling side did not apply the relay timeout. by @seefs001 in #2580
• fix: add tips for model management and channel testing by @seefs001 in #2582
• fix: batch add key backend deduplication by @seefs001 in #2581

New Contributors

• @zpc7 made their first contribution in #2554
• @atopos31 made their first contribution in #2425
• @wwalt1a made their first contribution in #2547
• @a4399518s made their first contribution in #2447

Full Changelog: v0.10.4...v0.10.5

Major Changes

• Channel parameter override now supports copy, trim_prefix, trim_suffix, ensure_prefix, ensure_suffix, trim_space, to_lower, to_upper, replace, and regex_replace operations.
• Doubao now supports the native /v1/responses format.
• io.net i18n support, and deployment operation UI/UX optimization.
• Check-in now supports integration with Cloudflare Turnstile.

主要变更

• 渠道参数覆盖增加 copy, trim_prefix, trim_suffix, ensure_prefix, ensure_suffix, trim_space, to_lower, to_upper, replace, and regex_replace 操作
• 豆包支持 /v1/responses 原生格式
• io.net i18n支持，部署操作UI/UX优化
• 签到支持接入Cloudflare Turnstile

What's Changed

• fix(checkin): prevent visual flicker when loading check-in component by @RedwindA in #2566
• remove duplicate condition in TaskLogsColumnDefs by @zpc7 in #2554
• feat: 支持仅使用x-api-key获取anthropic格式的模型列表 #2422 by @atopos31 in #2425
• feat: support HTTP_PROXY environment variable for default HTTP client by @wwalt1a in #2547
• fix: kling correct fail reason by @feitianbubu in #2532
• feat: support claude-haiku-4-5-20251001 on vertex by @prnake in #2393
• fix(task): 修复渠道配置多个key时无法获取任务的问题 by @a4399518s in #2447
• fix: CrossGroupRetry default false by @feitianbubu in #2570
• feat: add support for Doubao /v1/responses by @seefs001 in #2567
• feat: check-in feature integrates Turnstile security check by @seefs001 in #2571
• fix: gemini request -> openai tool call by @seefs001 in #2558
• fix: fix model deployment style issues, lint problems, and i18n gaps. by @seefs001 in #2556
• feat: add parameter coverage for more operations by @seefs001 in #2568

New Contributors

• @zpc7 made their first contribution in #2554
• @atopos31 made their first contribution in #2425
• @wwalt1a made their first contribution in #2547
• @a4399518s made their first contribution in #2447

Full Changelog: v0.10.5-checkin.1...v0.10.5-ionet.2

Major Changes

• Added user check-in function, which can be modified in operational settings.
• 新增用户签到功能，可在运营设置中修改

What's Changed

• feat(checkin): add check-in functionality by @Calcium-Ion in #2565

Full Changelog: v0.10.5-bailian.2...v0.10.5-checkin.1

修复wan2.6-i2v分辨率计费
视频生成页面预览优化

What's Changed

• feat: flush response writer after copying body by @feitianbubu in #2551

Full Changelog: v0.10.5-bailian.1...v0.10.5-bailian.2

主要更新

• 适配百炼wan2.6-i2v适配生成计费
• 适配百炼wan2.6系列生图与编辑，适配多图生成计费
• 适配百炼wan2.5系列生图与编辑
• 适配百炼z-image-turbo生图，适配prompt_extend计费

百炼真的是一个非常 棒 的平台

What's Changed

• feat: Add "wan2.6-i2v" video ratio configuration to Ali adaptor. by @seefs001 in #2544
• fix: glm 4.7 finish reason by @seefs001 in #2545

Full Changelog: v0.10.5-ionet.1...v0.10.5-bailian.1

What's Changed

• feat: map OpenAI developer role to Gemini system instructions by @RedwindA in #2536
• feat: ionet integrate by @seefs001 in #2105

Full Changelog: v0.10.4...v0.10.5-ionet.1

What's Changed

• feat: pyroscope integrate by @seefs001 in #2475
• fix: ensure overwrite works correctly when no missing models by @feitianbubu in #2154
• fix(i18n): disable namespace separator to fix URL display in translations by @RedwindA in #2530
• 🚀 fix(model-sync): avoid unnecessary upstream fetch while keeping ove… by @t0ng7u in #2528
• 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 by @seefs001 in #2513
• fix: add warning for pass through body by @seefs001 in #2512
• fix: 支持传入system_instruction和systemInstruction两种风格系统提示词参数名 by @seefs001 in #2450
• Refine French translations for UI conciseness by @comeback01 in #2455
• fix(gemini): handle minimal reasoning effort budget by @seefs001 in #2460
• fix: Fix Openrouter test errors and optimize error messages by @seefs001 in #2433
• feat: support first bind update password by @feitianbubu in #2520

Full Changelog: v0.10.3...v0.10.4

What's Changed

• 🔗 docs(readme): update documentation links to new site routing by @t0ng7u in #2486
• 修复claudeResponse流式请求空指针Panic by @feitianbubu in #2510
• Solve Claude Code crash issue by @JerryKwan in #2511
• 为Moonshot添加缓存tokens读取逻辑 by @shikaiwei1 in #2493
• fix: 修复 Anthropic 渠道缓存计费错误 by @1420970597 in #2477
• fix: revert model ratio by @seefs001 in #2524

New Contributors

• @JerryKwan made their first contribution in #2511
• @shikaiwei1 made their first contribution in #2493
• @1420970597 made their first contribution in #2477

Full Changelog: v0.10.2...v0.10.3

What's Changed

• fix: 模型设置增加针对Vertex渠道过滤content[].part[].functionResponse.id的选项，默认启用 by @seefs001 in #2483

Full Changelog: v0.10.1...v0.10.2

主要更新

• 支持在令牌中设置auto分组下是否启用跨分组重试

• 支持gpt模型-xhigh后缀
• 支持非流gpt-4o-mini-tts类模型计费，规则详见 #2434

What's Changed

• fix: 支持aws 通过全局参数透传或者渠道参数透传来 调用 by @zdwy5 in #2423
• fix: health check by @seefs001 in #2428
• feat(token): add cross-group retry option for token processing by @Calcium-Ion in #2426
• fix: correct sender format issues fix #1347 by @ion1ze in #2424
• feat(adaptor): add '-xhigh' suffix to reasoning effort options by @Calcium-Ion in #2429
• fix(channel_select): adjust priority retry logic for cross-group by @Calcium-Ion in #2430
• feat: support gpt tts series model quota calculate by @Calcium-Ion in #2434
• feat(auth): enhance IP restriction handling with CIDR support by @Calcium-Ion in #2445
• 🛡️ fix: prevent OOM on large/decompressed requests; skip heavy prompt… by @t0ng7u in #2452
• style: add card spacing by @TinsFox in #2474
• chore: add code-inspector-plugin integration by @TinsFox in #2476

New Contributors

• @zdwy5 made their first contribution in #2423
• @ion1ze made their first contribution in #2424
• @TinsFox made their first contribution in #2474

Full Changelog: v0.10.0...v0.10.1