i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-08 18:37:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
2,494 Commits 6 Branches 182 Tags
a728c090a9c0ba9d784348c5ddea3e1f7ffb361c
Commit Graph
51 Commits
Author SHA1 Message Date
MMEXA 25c49dd804 fix(data): keep terminal usage state monotonic 2026-07-12 05:45:37 +08:00
MMEXA dfa121dd5b feat(openai): align GPT-5.6 and Codex request contracts 2026-07-11 07:40:12 +08:00
elky 4bf5d4c044 Fix cache token accounting and tiered pricing 2026-07-10 15:13:12 +08:00
elky 7c32be46ca Mark sync usage active earlier 2026-07-01 02:21:20 +08:00
AAEE86 c255f29e98 Merge remote-tracking branch 'upstream/main' 2026-06-16 10:53:47 +08:00
elky 8edcbdcb29 feat(usage): expose request timing details 2026-06-10 09:16:15 +08:00
AAEE86 d5d3f09846 refactor(health): add dashboard overview and related drill-down 
- Replace health monitor tabs with a dashboard layout
- Add related health drill-down for endpoint, model, and provider cards
- Render provider health as cards and hide empty monitors
 2026-06-02 00:10:59 +08:00
AAEE86 7ffe33f867 feat(health): refine health monitor metrics 
- add TPS to model and provider health payloads

- exclude user-cancelled 499 requests from health statistics

- update model/provider health cards with average latency, average TTFB, TPS, and availability
 2026-06-01 18:34:51 +08:00
Entropy.Xu 7ed4b84654 feat(ccswitch): 添加一键导入和用量查询 2026-05-29 21:39:45 +08:00
fawney19 47886abd2b Preserve streaming usage timing on refresh 2026-05-28 16:33:10 +08:00
AAEE86 4ce056fe45 feat(health): add model and provider health monitoring 
- Rename the original health monitor to endpoint health monitor
- Add tab navigation for endpoint, model, and provider health views
- Add model health monitor cards with availability, latency, first-byte latency, and 60-point history
- Add admin-only provider health monitor with collapsible active-provider sections
- Show per-provider model health cards after expanding a provider
- Add backend model health and provider health monitor payload builders
- Add admin endpoint for provider health monitoring
- Add provider-scoped usage breakdown filtering for per-provider model statistics
- Add frontend API types and request helpers for model/provider health data
- Add demo mock data for model and provider health monitoring
- Fix model health timeline time-unit handling so request history segments render correctly

Verification:
- cargo fmt
- npm run type-check
- npm run build
- cargo test -p aether-gateway health_models
- cargo test -p aether-gateway health_providers
- cargo test -p aether-gateway gateway_exposes_frontdoor_manifest_without_proxying_upstream
 2026-05-28 12:00:20 +08:00
stabeyandClaude Opus 4.7 3330b2ac4c refactor(report-context): extract UPSTREAM_IS_STREAM_KEY constant 
The "upstream_is_stream" JSON key flows from the AI execution report
context producer (aether-ai-serving::report_context) through several
consumers — usage runtime metadata copy/move, gateway watchdog, sync
execution decision, observability handlers, and the per-driver usage
repositories. Each site spelled the key as a bare string literal, so a
producer-side rename would silently degrade every consumer to its
fallback (typically assuming streaming) with no compile-time signal.

Introduce a single pub const UPSTREAM_IS_STREAM_KEY in
aether-ai-formats (the lowest crate every consumer already depends on),
re-export from the crate root, and route producer + all map-style
consumers through it. The change is purely a string-literal → constant
swap; behaviour is identical.

Sites left as literals (intentional):
- `json!({"upstream_is_stream": ...})` macro keys, which must be string
  literals at the macro layer; these are also API-response payload
  field names (an external contract that should not silently track
  internal report-context renames).
- SQL column accessors (`try_get::<...>("upstream_is_stream")`), which
  refer to the database schema column, not the JSON key.
- Test fixtures and assertions, which validate the on-the-wire contract
  and should keep verifying the actual string.

Co-Authored-By: Claude Opus 4.7 <[email protected]>
 2026-05-21 15:26:42 +08:00
fawney19 57910f906d Preserve usage provider identity 2026-05-20 20:56:36 +08:00
RWDai 6d994917a0 Add usage client family read model field 2026-05-18 19:28:36 +08:00
AAEE86 bfbf7a4663 fix(usage): 统一用户排行榜 Token 统计口径 
- 将用户排行榜 Tokens 调整为与仪表盘今日 Token 一致
- 统一 effective input、cache creation fallback、cache read 计算规则
- 补齐 Postgres 聚合、admin 内存构建和内存仓库回退路径
- 增加缓存命中场景的统计口径测试
 2026-05-11 22:34:37 +08:00
Kayphoon 79cb9b502a feat(pool): add codex cycle stats mode 2026-05-07 00:07:32 +08:00
fawney19 6fbb867f5f Exclude unknown providers from usage aggregations 2026-05-06 13:40:18 +08:00
fawney19 887a58d639 Fix usage provider stats and performance analysis UI 2026-05-06 09:29:12 +08:00
fawney19 2eb4afbec4 Merge remote-tracking branch 'origin/pr/384' into codex/pr-376-377-383-384-combined 
# Conflicts:
#	frontend/src/views/admin/PerformanceAnalysis.vue
 2026-05-06 02:39:53 +08:00
fawney19 cf27773582 feat: improve admin performance analysis 2026-05-06 02:01:32 +08:00
mayrain 6b6d32b4a3 feat(usage): 新增输出速度统计与请求详情性能分析 
- 把 upstream_is_stream 物化到 usage 与 billing facts，避免 Provider 聚合回连 public.usage
- 统一前端标准/流式 TPS 计算与显示，流式按首字后生成耗时计算
- 新增请求详情抽屉展示单请求输出速度与 Provider 聚合 TPS
 2026-05-05 17:34:12 +08:00
mayrain 53fa33b0c5 fix(dashboard): 修复仪表盘与明细统计数值不一致并重建 cost_savings 聚合 
- 统一 dashboard 聚合与 raw 查询的 token 计算，拆分今日节省和周期节省
- cache savings 改用 input price 估算未命中成本，修复历史 cost_savings 偏高
- raw 查询 total_tokens 改用 effective_input + output + cache_creation + cache_read 公式
- 新增独立 backfill 重建历史 cost_savings 聚合表，保留已发布 backfill 不变
 2026-05-05 17:33:16 +08:00
Entropy.Xu ff1ed8b57d feat(stats): 添加 Provider 性能统计分析 2026-05-05 11:24:16 +08:00
fawney19 0c9b5ddd77 Fix usage terminal state regression 2026-04-28 10:31:16 +08:00
fawney19 cf6228f525 feat(stats,rules): api_key 用量统计（total_tokens 字段 + 回填）与 body rules 新增 append/insert/regex_replace/name_style 操作 
- 新增迁移 20260422120000_add_api_key_usage_stats.sql，为 api_keys 表添加 total_tokens 列
- 新增回填 20260422120000_backfill_api_key_usage_stats.sql，按历史 usage 重建 api_key 维度汇总
- 在 UsageWriteRepository trait 中添加 rebuild_api_key_usage_stats，补齐 SQL/内存实现及上层调用链
- 内存实现中新增 apply_usage_stats_delta，支持增量更新 api_key 统计快照
- dev.sh：改进临时日志目录管理，并在网关异常退出时输出错误提示
- frontend EndpointFormDialog：将 append 操作从 insert 分支拆分，提供独立 path/value 输入 UI
- rules.rs：扩展 body rules 支持，新增 append/insert/regex_replace/name_style 操作及 WildcardSlice 路径段
 2026-04-22 20:16:57 +08:00
fawney19 a5e6bd3b62 feat(stats): 新增聚合读路径与回填机制并重构 dashboard/usage 读取链路 
- 新增 stats_user_summary 及 user_daily_provider/api_format/cost_savings 等聚合表
- 扩展 stats_daily/hourly 有效 token 与响应时间等字段，maintenance runtime 同步写入
- 新增 backfill 模块与 --apply-backfills 命令补齐历史聚合数据
- 重写 dashboard_filters、usage_heatmap、user_rollups 查询改走聚合表
- 同步更新 baseline_v2.sql 与 migration 集，README/dev.sh 补充回填用法
 2026-04-22 17:29:39 +08:00
AAEE86 6666992d01 feat(admin): 将用户管理的用量统计改为全量累计口径 (#314) 
- 新增按用户 ID 批量汇总 usage 的后端查询
- 在 /api/admin/users 中返回 request_count 和 total_tokens
- 移除用户管理页面额外的 usage 聚合请求
- 为管理端用户列表补充累计统计回归测试
 2026-04-19 01:26:22 +08:00
AAEE86andfawney19 bafb63a665 持久化 provider key 使用统计并移除 usage 汇总覆盖 (#313) 
* 持久化 provider key 使用统计并移除 usage 汇总覆盖

- 在 usage upsert 时按请求前后差值同步 provider_api_keys 统计
- 增加基于保留 usage 记录的 provider key 统计重建能力
- 号池管理列表直接读取 provider_api_keys 统计字段

* fix: harden provider key usage stats sync

---------

Co-authored-by: fawney19 <[email protected]>
 2026-04-19 01:02:09 +08:00
fawney19 3363592751 Refactor usage body capture and stream terminal reporting 2026-04-18 17:48:21 +08:00
fawney19 1e0bc61526 feat(gateway/data): 新增 usage 关键词搜索、缓存命中摘要、结算成本摘要及 dashboard 聚合查询能力 
- 新增 UsageAuditKeywordSearchQuery，支持多关键词、用户名、API Key 交叉过滤
- 新增 UsageCacheHitSummaryQuery/StoredUsageCacheHitSummary，统计请求缓存命中率
- 新增 UsageSettledCostSummaryQuery/StoredUsageSettledCostSummary，汇总结算成本
- 新增 UsageDashboardSummaryQuery、UsageBreakdownSummaryQuery 等 dashboard 聚合类型
- SQL 层实现对应查询方法，含 list_by_ids、list_usage_audits_by_keyword_search、count_usage_audits_by_keyword_search
- 将上述能力通过 GatewayDataState / AdminAppState 暴露给 handler 层
- user_me_usage 及 dashboard_filters 切换为新查询接口，移除旧的内存过滤逻辑
- 同步更新 memory 层及测试
 2026-04-17 01:00:38 +08:00
fawney19 65cd9dc3e5 fix(admin): 修复 usage 观测全表扫描并下推聚合查询 
- 收紧 admin usage/stats 默认时间范围和 active 轮询查询
- 将 summary/records/aggregation/time-series/leaderboard 下推到 SQL 侧
- 统一前端时间参数并补齐 admin usage/stats 回归测试
 2026-04-16 17:46:19 +08:00
fawney19 d805a28c9a feat: 请求候选追踪添加 proxy 元数据, 修复 usage 状态回退, 优化前端轮询 
- 在各 planner decision payload 中注入 proxy trace 信息 (node_id, node_name, url, source)
- request_candidate 报告上下文支持 proxy 字段, extra_data 合并逻辑改为 merge 而非覆盖
- SQL/内存仓库防止 usage status 从 streaming 回退到 pending
- 前端移除活跃请求完成时的全表刷新, active discovery 尊重 globalAutoRefresh 开关
 2026-04-16 11:57:42 +08:00
fawney19 43e7ad112f perf(usage): user-me usage 查询避免全量加载，默认限制 7 天范围 
- UsageAuditListQuery 新增 limit 字段，支持在 SQL 层 LIMIT
- user-me usage 端点无时间范围时默认查最近 7 天
- active usage 端点无 ids 过滤时限制查最近 1 小时
- InMemory 实现同步支持 limit truncate
 2026-04-15 16:25:57 +08:00
fawney19 4087e096f2 fix(usage): 为 InMemory 仓库补充 status 过滤逻辑 2026-04-15 09:53:52 +08:00
fawney19 98ad1172b0 perf(usage): heatmap 改为数据库端按天聚合查询 
将 admin 和 user heatmap 从逐条加载 usage audit 记录后在应用层聚合,
改为通过 SQL GROUP BY DATE 在数据库端直接按天汇总, 大幅减少数据传输量。

新增 UsageDailyHeatmapQuery / StoredUsageDailySummary 类型,
在 trait、SQL、内存实现中均补齐 summarize_usage_daily_heatmap 方法。

同时优化 docker-compose: postgres 增加空闲事务超时与 keepalive 参数,
gateway 增加健康检查配置。
 2026-04-15 02:11:32 +08:00
fawney19 53acfbabf6 refactor(gateway): 重构 ai pipeline 规划链路 2026-04-14 01:27:04 +08:00
fawney19 4fd2b4a014 fix(gateway): 修复 balance 刷新去重键冲突、usage 状态回退与测试竞态 
- balance_cache: 引入实例级 refresh key 防止多实例共享进程级 HashSet 冲突
- InMemoryUsageRepo: 阻止 pending/streaming 状态覆盖已终结(completed/failed/cancelled)记录
- usage 同步测试: 等待条件从 is_some() 改为检查 status=="completed" 避免竞态
- wallet 测试: 增加轮询等待 wallet 扣款完成
- 整理 import 语句与 tests 模块位置
 2026-04-13 16:48:05 +08:00
fawney19 5bb08e6aa4 feat(gateway): 重构 usage 数据层、迁移系统与系统导入 
数据库迁移:
- 引入 baseline v2 bootstrap，空库首次启动自动初始化
- 服务启动不再自动执行迁移，需显式 `--migrate` 运行
- 新增 pending migration 检测，schema 落后时拒绝启动

Usage 数据层:
- usage body 存储外部化为独立 blob 表
- 新增 HTTP audit 表拆分存储请求/响应头与 body ref
- 后台清理任务支持 legacy body ref 元数据迁移
- usage runtime 写入迁移到专用 tokio runtime（独立线程池, 8MB 栈）

系统导入/导出:
- 支持用户、API Keys、钱包数据的完整导入
- 兼容 legacy 与 v1.3+ 两种导出格式

其他改进:
- executor outcome 增加 runtime miss 诊断上下文
- 主 tokio runtime 栈大小调整为 8MB
- 前端 provider 管理支持 base URL 配置
- dev.sh 支持 --migrate 参数
 2026-04-13 14:01:22 +08:00
fawney19 848f99d3e5 merge(pr287): absorb remaining rust branch changes 
Absorb the remaining changes from PR #287 into aether-rust-pioneer after resolving conflicts locally and preserving the admin fixes already landed in this branch.

Closes #287
Co-authored-by: AAEE86 <[email protected]>
 2026-04-11 03:10:16 +08:00
fawney19 a54ac76688 fix(admin): restore pool key usage aggregates 2026-04-11 02:54:54 +08:00
AAEE86 174f11604a fix(data): 统一 usage 内存仓储时间戳单位并通过格式检查 
- 将 usage 内存仓储的秒级过滤条件转换为毫秒后再比较
- 汇总 provider api key 最近使用时间时将毫秒转换为秒
- upsert 在缺少 created_at 时默认写入毫秒时间戳
- 补充时间戳单位回归测试
- 调整 registry.rs 格式以通过 cargo fmt --all --check
 2026-04-10 22:23:26 +08:00
AAEE86 b1f6fff0a5 fix(gateway): 修复 local finalize 与 usage 聚合相关测试失败 
- 修正内存 usage 仓库的时间单位处理，恢复 stats/monitoring/dashboard/wallet/pool 聚合结果
- 允许 openai:compact 走 CLI 响应转换与本地 finalize cross-format 路径
- 更新 cross-format 测试夹具，显式启用 enable_format_conversion
- 调整 failover 测试优先级，消除候选平局导致的顺序不稳定
- 补齐 ai_pipeline 架构断言所需导入并清理残留 runtime 空目录
 2026-04-10 18:27:02 +08:00
fawney19 010ab127e2 feat: 扩展 cache creation token 细分统计与 effective_input_tokens 计费逻辑 
- 新增 cache_creation_ephemeral_5m/1h_input_tokens 字段，区分不同 TTL 的缓存写入 token
- 引入 effective_input_tokens（扣除 cache read 后的有效输入 token），暴露给 usage 接口
- billing 规则生成器支持 5m/1h ephemeral cache 独立定价与分级计费
- usage_mapper 增加 Claude/Anthropic 格式映射，修复 OpenAI responses 格式字段兼容性
- 迁移逻辑增强：支持 checksum 容错、applied/pending 数量日志、逐步执行信息输出
- executor 抽离 LocalExecutionRequestOutcome 类型，统一 sync/stream 路径返回语义
- provider-transport auth 层新增 complete passthrough headers 构建逻辑
- 前端 usage 类型全面补充 effective_input_tokens、cache_creation_tokens、total_input_context 字段
 2026-04-10 17:44:55 +08:00
AAEE86 82c3c33610 fix(build): 修复网关构建失败并收口候选选择与 finalize 回归 
- 补齐 DecisionTraceCandidate 新增字段，修复审计测试构造
- 修正 usage 内存仓库的 created_at_unix_ms 字段引用与秒/毫秒换算
- 将 build_minimal_candidate_selection 重构为输入对象，消除 clippy 参数过多问题
- 修复 admin global model created_at 旧字段残留引用
- 修复 openai:cli 与 openai:compact 同家族 finalize 在 needs_conversion=true 时的成功回落逻辑
- 清理 aether-gateway 中的 derive/default 与 needless borrow 等 clippy 问题
 2026-04-10 17:23:40 +08:00
AAEE86 677b8f5acb Merge remote-tracking branch 'upstream/aether-rust-pioneer' into rust 2026-04-10 15:08:32 +08:00
fawney19 5014e2f5fd refactor: 抽离 AI pipeline 与调度共享能力逻辑 2026-04-10 01:46:14 +08:00
AAEE86 0b3f619280 fix: 号池列表统计与最后使用时间显示 
- 为 usage 仓储新增按 provider_api_key_id 汇总请求数、Token、费用和最后使用时间的能力
- 在 /api/admin/pool/{provider_id}/keys 中优先使用 usage 汇总结果覆盖 request_count、total_tokens、total_cost_usd、last_used_at
- 补充数据层与网关侧回归测试，避免号池管理页统计全为 0 且最后使用为空
 2026-04-09 15:10:21 +08:00
fawney19 5d96d6673b refactor: 大规模模块拆分与代码精简，新增 ai-pipeline/data-contracts 独立 crate 
- 新增 aether-ai-pipeline 和 aether-data-contracts crate，将 pipeline 逻辑与数据契约从 gateway 中解耦
- 重构 admin handlers：拆分单体模块为 auth/billing/endpoint/features/model/observability/provider/system 等独立子模块
- 合并 chat/cli 重复代码路径：精简 conversion、finalize、planner 中的 sync/chat/cli 分支
- 重构 scheduler/executor/data 层，引入 facade 模式降低模块间耦合
- 移除冗余的 intent 模块，将 plan_fallback/policy/stream_path/sync_path 迁移至 executor
- 前端适配：调整 admin API 调用和 provider 模型测试对话框
 2026-04-07 02:50:19 +08:00
fawney19 8f26e1a31f refactor: 移除独立 hub/proxy/executor/gateway crate，统一为 gateway tunnel 架构 
- 删除 aether-hub、aether-proxy 独立项目及其 Dockerfile/配置
- 删除 crates/aether-executor 和 crates/aether-gateway 全部模块
- 新增 apps/ 目录作为应用入口
- 将 hub 概念重构为 gateway tunnel transport
- 将 executor 重构为 execution runtime
- 新增 tunnel.rs 合约定义和 testkit tunnel/execution_runtime 模块
- 更新 Python 服务层和测试适配新架构命名
 2026-04-03 14:59:58 +08:00
fawney19 ddf18fed9a feat: 扩展 Rust gateway 全功能模块，新增 billing/crypto/wallet crate 及完整数据层 
- 新增 aether-billing、aether-crypto、aether-wallet 独立 crate
- aether-data 扩展 repository 层：announcements、auth_modules、billing、
  candidate_selection、gemini_file_mappings、global_models、management_tokens、
  oauth_providers、proxy_nodes、quota、users、wallet 等模块
- aether-gateway 新增 api/auth/billing/control/middleware/scheduler/usage/
  video_tasks/hooks/maintenance/model_fetch/provider_transport 等功能模块
- 重构 executor decision 和 gateway state 为模块目录结构
- 新增 gateway router、frontdoor 路由层及对应测试
- Python 侧 API 路由重构，新增 compat/support 模块
- 前端 Logo 组件更新及 Provider 管理页面调整
 2026-03-31 19:19:04 +08:00