Warning
Experimental Plugin System / 实验性插件系统
自 v1.0.0-rc.27 起引入的实验性插件系统仍处于测试阶段，并涉及较大的架构调整。如遇问题，请及时反馈。
从 v1.0.0-rc.26 或更早版本升级的用户，必须重新配置所有视频模型价格；已完成该配置的用户无需重复操作。本版本仍不推荐用于生产环境。
The experimental plugin system introduced in v1.0.0-rc.27 remains under testing and includes major architectural changes. Please report any issues promptly.
Users upgrading from v1.0.0-rc.26 or earlier must reconfigure all video model prices. Users who have already completed this step do not need to repeat it. This release is still not recommended for production use.
Important
OpenRouter Compatibility / OpenRouter 兼容性说明
OpenRouter 渠道不再将任意以 -thinking 结尾的模型名自动解释为思考模式别名，以避免错误改写 kimi-k2-thinking 等真实模型 ID。
依赖旧行为的用户应改用 some-model@thinking:on，或通过渠道模型映射保留原有公开名称：{"some-model-thinking":"some-model@thinking:on"}。符合模型家族识别规则的 Claude 与 Gemini 旧式思考后缀仍受支持。
OpenRouter channels no longer interpret arbitrary model names ending in -thinking as reasoning aliases, preventing real model IDs such as kimi-k2-thinking from being rewritten.
If you relied on the old behavior, use some-model@thinking:on, or preserve the old public name with channel model mapping: {"some-model-thinking":"some-model@thinking:on"}. Recognized Claude and Gemini family thinking aliases remain supported.
New Features
- Added
gpt-6-astrato the OpenAI model list with built-in expression pricing for standard and long-context requests, including input, output, cache-read, and cache-write usage. Existing administrator pricing overrides take precedence. - Added explicit trailing
@key:valuemodel modifiers for non-pass-through relay requests:@thinking:on,@thinking:off,@thinking:adaptive, or@thinking:<budget>@effort:none|minimal|low|medium|high|xhigh|max@temperature:<number>and@topp:<number>
- Model modifiers override corresponding request-body fields and remain effective across channel model mapping. Modifiers on the mapped model take precedence over those on the requested model; repeated keys use the rightmost value.
- Added administrator-visible conversion diagnostics for modifier conflicts, duplicates, and provider-specific adjustments.
- Added
re:-prefixed Go regular expressions to Models that skip thinking suffix processing, allowing real model names containing@key:valueto bypass modifier parsing and validation. Unknown modifier keys and invalid values otherwise return HTTP 400.
Billing and Routing
- Added canonical billing names such as
base@effort:high@thinking:onandbase@thinking:on, with fallback to the base model when no matching variant price is configured. - Equivalent modifier variants share canonical pricing names. Numeric thinking-budget values,
temperature, andtoppdo not create separate canonical pricing variants. - Updated pricing settings and pricing synchronization to expose the effective built-in billing defaults used at runtime.
- Improved channel selection, model mapping, and token model-limit matching for models with modifiers or supported legacy aliases.
- Preserved existing legacy alias pricing and Gemini thinking-budget wildcard entries.
Fixes and Improvements
- Fixed implicit reasoning-effort remapping:
maxandxhighnow remain distinct through OpenAI Chat and Responses conversion paths. - Preserved native reasoning controls when no model modifier or protocol conversion requires adaptation, avoiding unnecessary normalization or rejection of provider-native values.
- Restricted generic legacy suffix parsing to recognized GPT/o-series, Claude, and Gemini model families, protecting real model names such as
qwen-maxandkimi-k2-thinking. - Applied thinking-suffix exemptions consistently across DeepSeek, Volcengine, and xAI adaptors.
- Improved Claude reasoning conversion by adapting unsupported combinations where possible and recording diagnostic warnings.
- In global or channel-level pass-through mode, model modifiers are forwarded unchanged without local parsing or validation.
- Improved HTTP 503 messages for models claimed by task plugins: errors now identify the claiming plugin and explain when it has no enabled channel in the selected group. Plugin model ownership remains unchanged (#7185).
- Fixed release builds selecting an incorrect version by resolving the version from the triggering Git tag.
Full Changelog: v1.0.0-rc.31...v1.0.0-rc.33