 wangbo
|
6c5daf29ca
|
perf(queue): 按策略动态扩缩异步 Worker
将 River 执行容量按平台模型与用户组的有效并发策略动态调整，并为长任务续租、并发租约原子抢占和限流退避补充保护。\n\n统一平台模型限流继承语义，兼容历史 platformLimits/modelLimits，并为三个迁移图像模型建立独立并发租约。补充管理端显式继承/覆盖配置、指标、单元测试及隔离 PostgreSQL 验收。\n\n验证：go test ./... -count=1；pnpm lint；pnpm test；pnpm build；隔离 PostgreSQL 并发原子性/续租测试；128 任务与三分钟长任务动态 Worker 验收。
|
2026-07-24 12:26:56 +08:00 |
|
|
wangbo
|
8b8e09cc22
|
fix(media): 支持大尺寸图像响应并补齐迁移契约
- 为图像协议放宽 JSON 响应上限并显式处理读取与超限错误
- 合并基础模型与平台能力，避免运行时丢失分辨率和比例约束
- 固化稳定 Gemini 图像模型的能力、计价和 preview 兼容别名
|
2026-07-24 08:40:30 +08:00 |
|
|
wangbo
|
8d86c4b3b3
|
feat(catalog): 统一模型调用身份并梳理生命周期
新增官方调用名、供应商真实名、显示名和兼容别名的独立契约，调整路由、目录聚合、管理端与 OpenAPI。
增加 Gemini、Qwen、DeepSeek、Claude 和 MiniMax 生命周期迁移、别名观测及引用保护，并补充数据库与聚合测试。
|
2026-07-22 20:23:36 +08:00 |
|
|
wangbo
|
8847d973a8
|
feat: add Responses API compatibility
|
2026-07-10 23:33:15 +08:00 |
|
|
wangbo
|
b7351f3b9b
|
feat(runtime): 适配推理模式开关
|
2026-07-06 02:03:03 +08:00 |
|
|
wangbo
|
24eb68cc09
|
feat: use message LCP cache affinity keys
|
2026-06-29 15:47:57 +08:00 |
|
|
wangbo
|
0e675e259c
|
feat: add runner failover rules and cache affinity
|
2026-06-28 20:50:23 +08:00 |
|
|
wangbo
|
6089aa6085
|
feat: support cloned voice deletion
|
2026-06-17 12:03:13 +08:00 |
|
|
wangbo
|
c4341335d7
|
feat: 支持 MiniMax 音色克隆和 2.8 语音模型
|
2026-06-17 02:13:21 +08:00 |
|
|
wangbo
|
dc14866210
|
迁移音频生成与语音合成到 gateway 并补充 simulation 测试
|
2026-06-07 10:26:57 +08:00 |
|
|
wangbo
|
2aeb47d6a5
|
fix(gateway): normalize model alias billing identity
|
2026-05-28 01:19:28 +08:00 |
|
|
wangbo
|
71950d2b4f
|
fix(rate-limits): treat empty policies as unlimited
|
2026-05-24 22:28:25 +08:00 |
|
|
wangbo
|
c2696e7bbe
|
feat(api): add load-aware client fallback
|
2026-05-12 16:59:51 +08:00 |
|
|
wangbo
|
7e220b7477
|
feat: add river-backed async task queue
|
2026-05-12 10:11:54 +08:00 |
|
|
wangbo
|
ba850a06c6
|
feat: improve model rate limit tracking
|
2026-05-12 03:22:29 +08:00 |
|
|
wangbo
|
0431cb8157
|
feat: improve model catalog aggregation
|
2026-05-11 17:44:57 +08:00 |
|
|
wangbo
|
ca7e76e815
|
fix gateway loopback validation chains
|
2026-05-11 08:48:02 +08:00 |
|
|
wangbo
|
0fc23d7eb8
|
feat(api): migrate volces client to gateway
|
2026-05-10 23:14:10 +08:00 |
|
|
wangbo
|
d59756a27c
|
chore: commit pending gateway changes
|
2026-05-10 22:34:15 +08:00 |
|
|
wangbo
|
fdcdcd477b
|
feat: implement AI gateway phase one runtime
|
2026-05-09 21:18:32 +08:00 |
|