Commit Graph
49 Commits
Author SHA1 Message Date
elky 579f2c7cc1 feat(security): harden gateway boundaries and usage policies
Consolidate subscription usage policy enforcement, privacy-safe persistence, and gateway security hardening into one reviewable change.

Includes bounded HTTP and execution envelopes, header and protocol guards, DNS and relay validation, authentication and secret projection hardening, secure backup/install paths, and regression coverage.
2026-09-04 03:45:52 +08:00
ZheFox 3dfc15963c Merge pull request #789 from zhefox/codex/fix-antigravity-quota
Codex/fix antigravity quota
2026-09-03 18:48:58 +08:00
elky 4291a91dc0 test(gateway): pass routing policy to affinity effects 2026-09-03 15:50:53 +08:00
ZheFox 587486ab0c Merge remote-tracking branch 'upstream/main' into codex/fix-antigravity-quota 2026-09-03 13:24:39 +08:00
fawney 2cb4d554aa feat(routing): consolidate scheduling strategy configuration 2026-09-03 11:05:59 +08:00
zhefox dbbe7b22ab fix(pool): isolate dynamic model quota buckets and 429 scheduling 2026-09-02 15:23:23 +08:00
AAEE86 71b54070e8 feat(gateway): Codex/OpenAI Responses WebSocket 代理模式
在 /v1/responses 上支持 WebSocket 升级,把客户端帧中继到上游 Codex /
OpenAI Responses WebSocket 端点,同时保持既有的路由、鉴权、配额与用量
语义:

- 路由与准入:control/route/ai.rs 识别 WebSocket 升级请求;
  websocket/ingress.rs 复用 API Key 鉴权、IP 规则与并发许可,并引入
  独立的 WebSocket 连接许可
- 中继:websocket/responses/* 按 connection / session / turn 分层,
  帧解析归一化、socket 写入有界、continuation 保持调度亲和性
- 配额:orchestration/codex_quota_breaker.rs 在账号配额耗尽时熔断并
  自动恢复,不再直接断开客户端连接
- 用量:每个 turn 的终态用量落库,request_metadata 记录
  websocket_mode / websocket_transport,管理端与 usage 视图暴露
  is_websocket
- 管理端:provider 可配置 Responses WebSocket 开关
2026-08-17 14:50:33 +08:00
elky 5b0c763086 fix(codex): fence concurrent quota updates 2026-08-14 09:28:07 +08:00
ZheFox 9d9316e434 Merge branch 'fawney19:main' into main 2026-07-28 13:56:34 +08:00
ZheFox f0f87b56a3 feat(providers): add credential-fenced OAuth key cleanup 2026-07-28 11:32:11 +08:00
elky 4148ab1931 fix(routing): harden routed pool scheduling 2026-07-27 22:06:28 +08:00
elky 531cf11025 feat(gateway): harden provider request execution
Preserve exact request payloads and model client surface and API operation explicitly.

Add Anthropic compatibility profiles, bounded stream commitment, and scoped OAuth retry behavior across provider transports.
2026-07-27 09:36:31 +08:00
elky 3606290ac8 fix(provider): harden Agent Identity OAuth lifecycle 2026-07-23 09:33:00 +08:00
elky fc92c4f431 perf(gateway): scale request hot paths for 20k streams
Shard and singleflight hot-path caches, batch and prioritize candidate and usage lifecycle persistence, and extend database and pressure-test instrumentation for 20k concurrent streams.
2026-07-22 02:11:08 +08:00
elky 8616fe6ee2 refactor(workspace): enforce layered crate boundaries 2026-07-15 23:47:19 +08:00
MMEXA 2316df5c9a feat(codex): align Search and execution protocol 2026-07-12 03:04:15 +08:00
elky 6f00e9fc67 Improve gateway transport and usage runtime 2026-06-25 22:36:27 +08:00
elky d336d1a7fa Improve gateway scheduling and runtime admission 2026-06-24 01:53:45 +08:00
elky 5b7805181b perf: queue request candidate persistence 2026-06-22 02:49:17 +08:00
elky f75894acbb perf: reduce gateway db pressure under load 2026-06-22 00:08:48 +08:00
elky 61bdd304b7 Handle inactive PAT owner as invalid OAuth token 2026-06-21 11:39:20 +08:00
zhefox 628a3a0d8d fix(ai-formats): support cyber policy failover and custom tool/audio passthrough 2026-06-17 02:33:14 +08:00
elky 68038c182b Distinguish expired OAuth token status 2026-06-12 19:43:59 +08:00
fawney19 1658925f52 Disable key circuit breaker for pool providers 2026-05-29 15:16:06 +08:00
fawney19 ccfc4cbddc Cache provider catalog lookups 2026-05-27 13:56:39 +08:00
RWDai 9859aec16c fix(gateway): evict pooled affinity after sibling key failures 2026-05-21 23:50:34 +08:00
RWDai 18fe5a4f11 fix(gateway): preserve affinity during adaptive retries 2026-05-21 21:56:26 +08:00
RWDai 965a8c79af fix(gateway): preserve cache affinity during health updates 2026-05-21 15:51:56 +08:00
fawney19 7e9ca88e00 fix: restore provider key circuit breaker backoff 2026-05-19 13:57:36 +08:00
MMEXA b480f3aaff fix(gateway): normalize Gemini Vertex embedding transport 2026-05-18 15:39:29 +00:00
fawney19 fa73655134 refactor: isolate dispatch scheduling core 2026-05-12 13:15:41 +08:00
fawney19 b9e62d1667 Implement generic pool member scoring and probing 2026-05-12 01:46:22 +08:00
fawney19 247ea9d1bd Restrict scheduler affinity to cache affinity mode 2026-05-11 14:06:49 +08:00
fawney19 e3574e1918 Track scheduler affinity epochs and key sorting 2026-05-11 01:45:49 +08:00
fawney19 bacb14e5f0 refactor: lazy pool key scheduling 2026-05-11 00:12:05 +08:00
fawney19 6247ac3edc refactor: extract runtime state backends 2026-05-08 00:18:12 +08:00
fawney19 10e679bb2f Add provider key cycle stats reset handling 2026-05-07 03:23:20 +08:00
fawney19 6dd7464793 Merge remote-tracking branch 'origin/aether-rust-pioneer' into pr-375-session-scope 2026-05-05 22:34:47 +08:00
fawney19 f959f02d40 Implement transport profile routing 2026-05-05 22:21:23 +08:00
fawney19 98421126f2 refactor: carry normalized client session affinity 2026-05-05 21:34:17 +08:00
fawney19 fce7e959e5 Add multi-database data layer
Introduce aether-data-schema and driver-specific schema generation for Postgres, MySQL, and SQLite.

Split data backends, lifecycle, repositories, and gateway runtime integration across database drivers.

Verified with cargo fmt --all --check, cargo clippy --workspace --all-targets -- -D warnings, and cargo test --workspace.
2026-05-05 18:27:36 +08:00
RWDai 628329e493 fix: scope scheduler effects by session 2026-05-05 12:25:07 +08:00
fawney19 099653f732 Cap Codex pool cooldowns and add key circuit breaker 2026-05-04 02:15:32 +08:00
fawney19 c130d0e2c9 refactor ai serving modules and crates 2026-05-02 13:23:54 +08:00
fawney19 33aa70c22b fix scheduler affinity candidate selection 2026-04-30 16:27:24 +08:00
fawney19 5b914aa78c migrate ai format conversion to responses adapters 2026-04-26 23:59:53 +08:00
fawney19 4374f53315 fix(adaptive): 修复 429 计数归零写入及 reset 语义
- sql.rs: UPDATE 时对 concurrent_429_count / rpm_429_count 加 COALESCE(, 0),避免 None 覆写为 NULL
- effects.rs: rpm_429_count 始终写入 Some(projection.rpm_429_count),不再过滤零值;新增 unknown-429 场景下零值持久化的单元测试
- adaptive.rs: reset 接口将两个计数字段置为 Some(0) 而非 None,与数据库默认语义对齐;同步修正集成测试断言
- docker-compose.build.yml: 补充 AETHER_GATEWAY_AUTO_PREPARE_DATABASE 默认开启
- README.md: 同步说明 build compose 也已默认开启自动迁移
2026-04-22 22:16:51 +08:00
fawney19 c1b9d94c84 feat(adaptive): 完善自适应 RPM 学习并将 Pool 调度状态与健康分解耦
- orchestration 新增 AdaptiveSuccess 效果,在成功回报路径上根据利用率窗口扩张 learned_rpm_limit
- 429 路径改用 429_observation/adjustment 记录以及基于历史的置信度评估,新增 last_rpm_peak 边界字段
- Pool 调度状态不再因 health_score 低或熔断而降级/拦截,前端同步移除相关按钮与文案兜底
- 新增前端 poolTrace 工具(附测试)承接原 HorizontalRequestTimeline 内的候选合并逻辑
2026-04-20 00:27:48 +08:00
fawney19 569242d72f refactor gateway orchestration and failover effects 2026-04-18 11:35:11 +08:00