From b3d3f48c40cc262a8066da726ca0cca14a3cd6d0 Mon Sep 17 00:00:00 2001
From: Sycun <165354365+Sycun@users.noreply.github.com>
Date: Sun, 11 Oct 2026 22:30:30 +0800
Subject: [PATCH 1/5] feat: add detailed token usage monitoring and cache write
metrics
---
docs/zh-CN/token-usage-monitoring.md | 54 +++++++
go.mod | 12 +-
go.sum | 12 ++
internal/database/model_token_usage.go | 26 ++--
internal/database/model_token_usage_test.go | 41 ++++-
internal/database/schema_reconcile_test.go | 1 +
internal/database/schemas/application.sql | 1 +
.../multiagent/eino_run_usage_accumulator.go | 14 +-
.../eino_run_usage_accumulator_test.go | 22 +++
internal/openai/eino_http.go | 1 +
internal/openai/eino_sse_sanitizer.go | 7 +-
internal/openai/eino_usage_normalizer.go | 90 +++++++++++
internal/openai/eino_usage_normalizer_test.go | 70 +++++++++
web/static/css/style.css | 22 +++
web/static/i18n/en-US.json | 36 ++++-
web/static/i18n/ru-RU.json | 35 ++++-
web/static/i18n/zh-CN.json | 36 ++++-
web/static/js/chat-scroll-refresh.test.cjs | 2 +-
web/static/js/chat.js | 7 +
web/static/js/dashboard.js | 141 +++++++++++++++++-
web/static/js/hitl-approval-ui.test.cjs | 4 +-
web/static/js/monitor.js | 6 +-
web/static/js/token-usage-analysis.test.cjs | 43 ++++++
web/static/js/turn-duration-refresh.test.cjs | 2 +
web/static/js/webshell.js | 3 +
web/templates/index.html | 23 ++-
26 files changed, 666 insertions(+), 45 deletions(-)
create mode 100644 docs/zh-CN/token-usage-monitoring.md
create mode 100644 internal/openai/eino_usage_normalizer.go
create mode 100644 internal/openai/eino_usage_normalizer_test.go
create mode 100644 web/static/js/token-usage-analysis.test.cjs
diff --git a/docs/zh-CN/token-usage-monitoring.md b/docs/zh-CN/token-usage-monitoring.md
new file mode 100644
index 00000000..f8c844b2
--- /dev/null
+++ b/docs/zh-CN/token-usage-monitoring.md
@@ -0,0 +1,54 @@
+# Token 用量监控:调研与实现
+
+调研时间:2026-10-11。
+
+## 调研结论
+
+| 参考 | 官方能力 | 本项目采用的设计 |
+| --- | --- | --- |
+| [ZCode 使用统计](https://zcode.z.ai/cn/docs/usage-stats) | 本地会话统计与远端编程套餐额度分别展示;支持时间范围、日趋势和模型占比 | 首页增加可展开的本地用量面板,提供 7/30/90 天、日趋势、模型占比与明细 |
+| [DeepSeek 上下文缓存](https://api-docs.deepseek.com/guides/kv_cache/) | 响应 usage 的 `prompt_cache_hit_tokens` / `prompt_cache_miss_tokens` 区分输入缓存命中和未命中 | 将命中字段补入 OpenAI 标准缓存读取字段;不把未命中错误映射为缓存写入 |
+| [Eino v0.9.21](https://github.com/cloudwego/eino/releases/tag/v0.9.21)、[schema PR #1309](https://github.com/cloudwego/eino/pull/1309) | 稳定版新增 `PromptTokenDetails.CacheWriteTokens`,原有缓存读取、输入、输出、推理字段继续保留 | 使用稳定版的标准字段贯穿流式归并、运行汇总、数据库和 UI |
+| [Eino-ext PR #1015](https://github.com/cloudwego/eino-ext/pull/1015) | 模型适配器传递缓存写入计数 | 升级 agenticclaude 0.1.7、agenticopenai 0.2.4 与对应 OpenAI ACL,而非仅升级框架 |
+| [Eino 回调与 Trace](https://www.cloudwego.io/docs/eino/quick_start/chapter_06_callback_and_trace/) | 组件回调可收集模型生命周期、用量与耗时 | 保留现有运行事件采集;未来要覆盖所有内部调用,应另外设计统一模型调用账本 |
+
+版本已通过 Go module 解析和本地源码确认;未采用 0.10 alpha。DeepSeek 原始字段当前不会自动进入 Eino 的标准缓存读取计数,因此在项目现有兼容 HTTP 层补齐,覆盖普通 JSON 和 SSE 流式响应。已有标准 `cached_tokens` 优先,未知字段使用 RawMessage 保存,避免浮点转换损失数字精度。
+
+## 统计口径
+
+- `promptTokens`:模型返回的全部输入。
+- `completionTokens`:全部输出,包括供应商计入其中的推理。
+- `totalTokens`:使用供应商的总量;缺省时由输入加输出补齐。
+- `cachedTokens`:输入中的缓存读取部分。
+- `cacheWriteTokens`:输入中的缓存写入部分。
+- `reasoningTokens`:输出中的推理部分。
+- 缓存读取、写入、推理都是细分,不能再加到总量。缓存读取占输入的比例为 `cachedTokens / promptTokens`;没有输入时显示破折号。
+- 一个流式模型输出可能多次返回累计计数,沿用按字段取最大值的归并方式,整条输出结束后只加入一次运行汇总。部分输出发生错误时,仍可保留已返回用量。
+
+DeepSeek 的未命中输入不等于 Claude 的缓存写入。不能根据文本长度推导账单级计数,也不能根据缺失字段断言供应商未使用缓存。旧记录的新增字段默认为 0,表示未记录该细分。
+
+## 功能入口与数据流
+
+点击首页「Token 用量」卡片或「查看用量详情」展开面板。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。沿用首页自动刷新和请求取消机制。
+
+运行事件 → 流式/非流式用量累加 → `eino_usage_summary` → `process_details` 与 `model_token_usage` → 现有 `/api/usage/tokens`、对话用量接口 → 首页与聊天摘要。
+
+新增 `model_token_usage.cache_write_tokens INTEGER NOT NULL DEFAULT 0`。启动时现有声明式 SQLite schema reconciliation 自动补列;旧数据库无需手工执行迁移。现有事件 ID 幂等写入、外键删除关联和历史回填继续生效。日分组按服务本地时区显示,与首页「今日」边界一致。
+
+面板采用文本节点渲染供应商模型名称,表格在手机上局部横向滚动,提供中文、英文、俄文标签。聊天轮次 tooltip、主对话与 WebShell 时间线均增加缓存写入字段。
+
+## 当前边界与后续方向
+
+统计基于已记录的 Agent 输出事件,包括已有采集链路中的子 Agent,**不是全站 API 请求账本**。摘要压缩、检索 embedding、隐藏的模型调用、没有返回 usage 的请求不能由当前链路完整覆盖;因请求取消丢失最终 usage 的消耗也无法还原。
+
+模型排行按运行配置的模型名称归类,发生 failover 的运行可能混合多个模型,不能据此核算逐模型账单。近期列表每项是运行汇总,不是单次 HTTP 请求;模型调用次数也仅统计返回了非空 usage 的输出。
+
+本次不展示费用或套餐剩余额度。自定义中转渠道和订阅套餐的价格、计费方式不同,token 乘固定单价无法可靠代表费用。下一步如需要完整成本管理,应先建设按请求记录的账本:调用来源、真实供应商与模型、成功/错误/取消、耗时、TTFT、usage 是否返回、价格版本和币种;统一覆盖主/子 Agent、压缩、重试、embedding,单独对接供应商额度接口。
+
+## 验证
+
+- `go test ./...`:全仓通过。
+- `node --test web/static/js/*.test.cjs`:295 项通过。
+- 针对缓存写入的保存/分组/近期记录、旧 schema 补列、用户可见范围、流式去重和总量回退添加回归测试。
+- DeepSeek 普通 JSON/SSE 的缓存字段转换、标准字段优先、错误/终止块保持、超大数值精度验证通过。
+- 浏览器使用合成数据验证桌面、390px 手机、深色模式、模型名称转义、空数据与接口不可用状态;没有读取真实运行数据库,也没有调用付费模型。
diff --git a/go.mod b/go.mod
index 894b3864..7d319ebd 100644
--- a/go.mod
+++ b/go.mod
@@ -7,14 +7,14 @@ go 1.25.0
require (
github.com/bwmarrin/discordgo v0.29.0
github.com/bytedance/sonic v1.15.0
- github.com/cloudwego/eino v0.9.14
+ github.com/cloudwego/eino v0.9.21
github.com/cloudwego/eino-ext/adk/backend/local v0.2.6
github.com/cloudwego/eino-ext/components/document/loader/file v0.0.0-20260427010451-749e3706378b
github.com/cloudwego/eino-ext/components/document/transformer/splitter/markdown v0.0.0-20260427010451-749e3706378b
github.com/cloudwego/eino-ext/components/document/transformer/splitter/recursive v0.0.0-20260427010451-749e3706378b
github.com/cloudwego/eino-ext/components/embedding/openai v0.0.0-20260427010451-749e3706378b
- github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.3
- github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.1
+ github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.7
+ github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.4
github.com/cloudwego/eino-ext/components/model/openai v0.1.13
github.com/creack/pty v1.1.24
github.com/disintegration/imaging v1.6.2
@@ -74,7 +74,7 @@ require (
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/cloudwego/base64x v0.1.6 // indirect
- github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260527084435-846f52bd97c6 // indirect
+ github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260924031408-10df7cac3f6d // indirect
github.com/dlclark/regexp2 v1.10.0 // indirect
github.com/dustin/go-humanize v1.0.1 // indirect
github.com/evanphx/json-patch v0.5.2 // indirect
@@ -105,11 +105,11 @@ require (
github.com/leodido/go-urn v1.2.4 // indirect
github.com/mailru/easyjson v0.9.0 // indirect
github.com/mattn/go-isatty v0.0.19 // indirect
- github.com/meguminnnnnnnnn/go-openai v0.1.2 // indirect
+ github.com/meguminnnnnnnnn/go-openai v0.1.6 // indirect
github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/nikolalohinski/gonja v1.5.3 // indirect
- github.com/openai/openai-go/v3 v3.35.0 // indirect
+ github.com/openai/openai-go/v3 v3.44.0 // indirect
github.com/pb33f/ordered-map/v2 v2.3.1 // indirect
github.com/pelletier/go-toml/v2 v2.2.3 // indirect
github.com/pkg/errors v0.9.1 // indirect
diff --git a/go.sum b/go.sum
index c10b3fa3..cc4267ea 100644
--- a/go.sum
+++ b/go.sum
@@ -81,6 +81,8 @@ github.com/cloudwego/base64x v0.1.6 h1:t11wG9AECkCDk5fMSoxmufanudBtJ+/HemLstXDLI
github.com/cloudwego/base64x v0.1.6/go.mod h1:OFcloc187FXDaYHvrNIjxSe8ncn0OOM8gEHfghB2IPU=
github.com/cloudwego/eino v0.9.14 h1:suNVibjtkPMiW7csFBdBqN3FRG0nRlCqoGKE7t0UDwY=
github.com/cloudwego/eino v0.9.14/go.mod h1:OBD1mrkfkt/pJa4rkg1P0VnaMeOVl7l8IAdEqY//3IQ=
+github.com/cloudwego/eino v0.9.21 h1:kBAyAjsnPq5NDWjt0VdmP9HY/XVUHs05LoeqybudPRQ=
+github.com/cloudwego/eino v0.9.21/go.mod h1:OBD1mrkfkt/pJa4rkg1P0VnaMeOVl7l8IAdEqY//3IQ=
github.com/cloudwego/eino-ext/adk/backend/local v0.2.6 h1:pxKAWcveIBWrbz28H2bDAMyJZnhysa9bh2Kh5s7iH7s=
github.com/cloudwego/eino-ext/adk/backend/local v0.2.6/go.mod h1:uJlpYclMA2ScgUlHWHu2om+DDguV2Lzc+TNulWBXqfo=
github.com/cloudwego/eino-ext/components/document/loader/file v0.0.0-20260427010451-749e3706378b h1:GIOC/VnXuSQx79mnQ3HgMvECjtyqvpJipmSUTFFfVsc=
@@ -93,12 +95,18 @@ github.com/cloudwego/eino-ext/components/embedding/openai v0.0.0-20260427010451-
github.com/cloudwego/eino-ext/components/embedding/openai v0.0.0-20260427010451-749e3706378b/go.mod h1:zyPrZT2bO6LyRJgVksQowR18jVgyLSvqK93hnO53/Lc=
github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.3 h1:nfO9jUPhIKTHDPyL7rso6y7Mx8cAmrIgkeJC6KqTuXI=
github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.3/go.mod h1:/dX1P7HNC7D3/nYLDoXBvdKAFnGS4tBbtJ8NrkaXuUk=
+github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.7 h1:oxvyuAdZLlKSWYrzXwXS63AokgC3TqSljrzCGNRi4JA=
+github.com/cloudwego/eino-ext/components/model/agenticclaude v0.1.7/go.mod h1:LsIyLkRviQtfJsGYP6MX9PwqCX4jMtVxR4zR2A7ZB+g=
github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.1 h1:bIMyUxEZdBEofWbXQCozfGxXCsbyNjpZcRMfW+Kt5u0=
github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.1/go.mod h1:84jUcVAcmlGDRVX0ExABVJEfrIaplaAeRbjFYW9mzkI=
+github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.4 h1:M5ODiB1UaYV0I/dL2dmgc/HfZ2WUBV0saM9Tkhk2IDg=
+github.com/cloudwego/eino-ext/components/model/agenticopenai v0.2.4/go.mod h1:AfLNKxrTFFkJbCWSvOtqKK1ZXEp0hpe26CBQ8GSf5zo=
github.com/cloudwego/eino-ext/components/model/openai v0.1.13 h1:5XHRTiTD5bt9KQrMHcfvuWNklEC3tpm3XHejdozt9vM=
github.com/cloudwego/eino-ext/components/model/openai v0.1.13/go.mod h1:mgIoqYYOc0eECCqvLbEYpOJrQNTNxkwXzSJzFU+v5sQ=
github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260527084435-846f52bd97c6 h1:ES/xufN5eqJ3h+9tw/tq6F8kkgnAxBAHVUB6nqKsIDU=
github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260527084435-846f52bd97c6/go.mod h1:5Xj74dGrfHo1z7I07Fzp3SlTF7Bt4tss3A2FSt8SqQ4=
+github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260924031408-10df7cac3f6d h1:FaBHOMj/ZDBmtsI9UMoDMDu9CNZPbjJwK/O26JFuZ8k=
+github.com/cloudwego/eino-ext/libs/acl/openai v0.1.18-0.20260924031408-10df7cac3f6d/go.mod h1:6yg0Rv7B3jZCQPc/C5s13PNnVewQdaRxOp2OMru7Yw4=
github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
github.com/cncf/xds/go v0.0.0-20251210132809-ee656c7534f5 h1:6xNmx7iTtyBRev0+D/Tv1FZd4SCg8axKApyNyRsAt/w=
github.com/cncf/xds/go v0.0.0-20251210132809-ee656c7534f5/go.mod h1:KdCmV+x/BuvyMxRnYBlmVaq4OLiKW6iRQfvC62cvdkI=
@@ -272,6 +280,8 @@ github.com/mattn/go-sqlite3 v1.14.18 h1:JL0eqdCOq6DJVNPSvArO/bIV9/P7fbGrV00LZHc+
github.com/mattn/go-sqlite3 v1.14.18/go.mod h1:2eHXhiwb8IkHr+BDWZGa96P6+rkvnG63S2DGjv9HUNg=
github.com/meguminnnnnnnnn/go-openai v0.1.2 h1:iXombGGjqjBrmE9WaSidUhhi3YQhf42QTHvHLMkgvCA=
github.com/meguminnnnnnnnn/go-openai v0.1.2/go.mod h1:qs96ysDmxhE4BZoU45I43zcyfnaYxU3X+aRzLko/htY=
+github.com/meguminnnnnnnnn/go-openai v0.1.6 h1:c74nk9F3+/agOd09eHeQt/Ayty4pw54X2Dj5JHdxcys=
+github.com/meguminnnnnnnnn/go-openai v0.1.6/go.mod h1:qs96ysDmxhE4BZoU45I43zcyfnaYxU3X+aRzLko/htY=
github.com/mgutz/ansi v0.0.0-20170206155736-9520e82c474b h1:j7+1HpAFS1zy5+Q4qx1fWh90gTKwiN4QCGoY9TWyyO4=
github.com/mgutz/ansi v0.0.0-20170206155736-9520e82c474b/go.mod h1:01TrycV0kFyexm33Z7vhZRXopbI8J3TDReVlkTgMUxE=
github.com/modelcontextprotocol/go-sdk v1.3.1 h1:TfqtNKOIWN4Z1oqmPAiWDC2Jq7K9OdJaooe0teoXASI=
@@ -300,6 +310,8 @@ github.com/onsi/gomega v1.40.0 h1:Vtol0e1MghCD2ZVIilPDIg44XSL9l2QAn8ZNaljWcJc=
github.com/onsi/gomega v1.40.0/go.mod h1:M/Uqpu/8qTjtzCLUA2zJHX9Iilrau25x1PdoSRbWh5A=
github.com/openai/openai-go/v3 v3.35.0 h1:109x3epXMSE423KW2euR506GGFezcEt0s87MoWejpH0=
github.com/openai/openai-go/v3 v3.35.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo=
+github.com/openai/openai-go/v3 v3.44.0 h1:kkGh+jb/sKfSh5P74Jk5mCRufaQ0q7oH+lq+pNlWjsk=
+github.com/openai/openai-go/v3 v3.44.0/go.mod h1:cdufnVK14cWcT9qA1rRtrXx4FTRsgbDPW7Ia7SS5cZo=
github.com/pb33f/ordered-map/v2 v2.3.1 h1:5319HDO0aw4DA4gzi+zv4FXU9UlSs3xGZ40wcP1nBjY=
github.com/pb33f/ordered-map/v2 v2.3.1/go.mod h1:qxFQgd0PkVUtOMCkTapqotNgzRhMPL7VvaHKbd1HnmQ=
github.com/pelletier/go-toml/v2 v2.2.3 h1:YmeHyLY8mFWbdkNWwpr+qIL2bEqT0o95WSdkNHvL12M=
diff --git a/internal/database/model_token_usage.go b/internal/database/model_token_usage.go
index 426bf5f5..6452b717 100644
--- a/internal/database/model_token_usage.go
+++ b/internal/database/model_token_usage.go
@@ -30,6 +30,7 @@ type ModelTokenUsage struct {
PromptTokens int64 `json:"promptTokens"`
CompletionTokens int64 `json:"completionTokens"`
TotalTokens int64 `json:"totalTokens"`
+ CacheWriteTokens int64 `json:"cacheWriteTokens"`
CachedTokens int64 `json:"cachedTokens"`
ReasoningTokens int64 `json:"reasoningTokens"`
CreatedAt time.Time `json:"createdAt"`
@@ -43,6 +44,7 @@ type ModelTokenUsageSummary struct {
PromptTokens int64 `json:"promptTokens"`
CompletionTokens int64 `json:"completionTokens"`
TotalTokens int64 `json:"totalTokens"`
+ CacheWriteTokens int64 `json:"cacheWriteTokens"`
CachedTokens int64 `json:"cachedTokens"`
ReasoningTokens int64 `json:"reasoningTokens"`
}
@@ -56,6 +58,7 @@ type ModelTokenUsageBreakdown struct {
PromptTokens int64 `json:"promptTokens"`
CompletionTokens int64 `json:"completionTokens"`
TotalTokens int64 `json:"totalTokens"`
+ CacheWriteTokens int64 `json:"cacheWriteTokens"`
CachedTokens int64 `json:"cachedTokens"`
ReasoningTokens int64 `json:"reasoningTokens"`
}
@@ -100,6 +103,7 @@ func modelTokenUsageFromProcessDetail(messageID, conversationID, processDetailID
CompletionTokens: usageInt64(m["completionTokens"]),
TotalTokens: usageInt64(m["totalTokens"]),
CachedTokens: usageInt64(m["cachedTokens"]),
+ CacheWriteTokens: usageInt64(m["cacheWriteTokens"]),
ReasoningTokens: usageInt64(m["reasoningTokens"]),
}
if usage.TotalTokens == 0 && (usage.PromptTokens > 0 || usage.CompletionTokens > 0) {
@@ -108,7 +112,7 @@ func modelTokenUsageFromProcessDetail(messageID, conversationID, processDetailID
if usage.ProcessDetailID == "" || usage.MessageID == "" || usage.ConversationID == "" {
return ModelTokenUsage{}, false
}
- if usage.ModelCalls == 0 && usage.TotalTokens == 0 && usage.PromptTokens == 0 && usage.CompletionTokens == 0 && usage.CachedTokens == 0 && usage.ReasoningTokens == 0 {
+ if usage.ModelCalls == 0 && usage.TotalTokens == 0 && usage.PromptTokens == 0 && usage.CompletionTokens == 0 && usage.CachedTokens == 0 && usage.CacheWriteTokens == 0 && usage.ReasoningTokens == 0 {
return ModelTokenUsage{}, false
}
return usage, true
@@ -224,9 +228,9 @@ func (db *DB) UpsertModelTokenUsage(usage ModelTokenUsage) error {
INSERT INTO model_token_usage (
id, process_detail_id, message_id, conversation_id, project_id,
source, orchestration, reason, model, model_calls,
- prompt_tokens, completion_tokens, total_tokens, cached_tokens, reasoning_tokens,
+ prompt_tokens, completion_tokens, total_tokens, cached_tokens, cache_write_tokens, reasoning_tokens,
created_at, updated_at
-) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
ON CONFLICT(process_detail_id) DO UPDATE SET
message_id = excluded.message_id,
conversation_id = excluded.conversation_id,
@@ -240,12 +244,13 @@ ON CONFLICT(process_detail_id) DO UPDATE SET
completion_tokens = excluded.completion_tokens,
total_tokens = excluded.total_tokens,
cached_tokens = excluded.cached_tokens,
+ cache_write_tokens = excluded.cache_write_tokens,
reasoning_tokens = excluded.reasoning_tokens,
created_at = excluded.created_at,
updated_at = excluded.updated_at`,
usage.ID, usage.ProcessDetailID, usage.MessageID, usage.ConversationID, projectValue,
usage.Source, usage.Orchestration, usage.Reason, usage.Model, usage.ModelCalls,
- usage.PromptTokens, usage.CompletionTokens, usage.TotalTokens, usage.CachedTokens, usage.ReasoningTokens,
+ usage.PromptTokens, usage.CompletionTokens, usage.TotalTokens, usage.CachedTokens, usage.CacheWriteTokens, usage.ReasoningTokens,
createdAt, now,
)
if err != nil {
@@ -318,7 +323,7 @@ func (db *DB) GetModelTokenUsageStats(filter ModelTokenUsageFilter) (*ModelToken
return nil, err
}
byDay, err := db.queryModelTokenUsageBreakdown(
- "SELECT date(mtu.created_at) AS k, date(mtu.created_at) AS label, "+modelTokenUsageSummarySelect("mtu")+" FROM model_token_usage mtu JOIN conversations c ON c.id = mtu.conversation_id"+where+" GROUP BY date(mtu.created_at) ORDER BY k DESC LIMIT ?",
+ "SELECT date(mtu.created_at, 'localtime') AS k, date(mtu.created_at, 'localtime') AS label, "+modelTokenUsageSummarySelect("mtu")+" FROM model_token_usage mtu JOIN conversations c ON c.id = mtu.conversation_id"+where+" GROUP BY date(mtu.created_at, 'localtime') ORDER BY k DESC LIMIT ?",
append(args, filter.Days)...,
)
if err != nil {
@@ -363,7 +368,8 @@ COALESCE(SUM(%sprompt_tokens), 0),
COALESCE(SUM(%scompletion_tokens), 0),
COALESCE(SUM(%stotal_tokens), 0),
COALESCE(SUM(%scached_tokens), 0),
-COALESCE(SUM(%sreasoning_tokens), 0)`, p, p, p, p, p, p, p)
+COALESCE(SUM(%scache_write_tokens), 0),
+COALESCE(SUM(%sreasoning_tokens), 0)`, p, p, p, p, p, p, p, p)
}
func buildModelTokenUsageWhere(filter ModelTokenUsageFilter, usageAlias, convAlias string) (string, []interface{}) {
@@ -394,7 +400,7 @@ func (db *DB) queryModelTokenUsageSummary(query string, args ...interface{}) (Mo
var s ModelTokenUsageSummary
err := db.QueryRow(query, args...).Scan(
&s.Events, &s.ModelCalls, &s.PromptTokens, &s.CompletionTokens,
- &s.TotalTokens, &s.CachedTokens, &s.ReasoningTokens,
+ &s.TotalTokens, &s.CachedTokens, &s.CacheWriteTokens, &s.ReasoningTokens,
)
if err != nil {
return s, fmt.Errorf("查询模型Token用量汇总失败: %w", err)
@@ -413,7 +419,7 @@ func (db *DB) queryModelTokenUsageBreakdown(query string, args ...interface{}) (
var row ModelTokenUsageBreakdown
if err := rows.Scan(
&row.Key, &row.Label, &row.Events, &row.ModelCalls, &row.PromptTokens,
- &row.CompletionTokens, &row.TotalTokens, &row.CachedTokens, &row.ReasoningTokens,
+ &row.CompletionTokens, &row.TotalTokens, &row.CachedTokens, &row.CacheWriteTokens, &row.ReasoningTokens,
); err != nil {
return nil, fmt.Errorf("扫描模型Token用量分组失败: %w", err)
}
@@ -438,7 +444,7 @@ func (db *DB) ListModelTokenUsage(filter ModelTokenUsageFilter) ([]ModelTokenUsa
SELECT mtu.id, mtu.process_detail_id, mtu.message_id, mtu.conversation_id,
COALESCE(mtu.project_id, ''), mtu.source, mtu.orchestration, mtu.reason, mtu.model,
mtu.model_calls, mtu.prompt_tokens, mtu.completion_tokens, mtu.total_tokens,
- mtu.cached_tokens, mtu.reasoning_tokens, mtu.created_at, mtu.updated_at
+ mtu.cached_tokens, mtu.cache_write_tokens, mtu.reasoning_tokens, mtu.created_at, mtu.updated_at
FROM model_token_usage mtu
JOIN conversations c ON c.id = mtu.conversation_id`+where+`
ORDER BY mtu.created_at DESC, mtu.rowid DESC
@@ -455,7 +461,7 @@ LIMIT ?`, args...)
&u.ID, &u.ProcessDetailID, &u.MessageID, &u.ConversationID, &u.ProjectID,
&u.Source, &u.Orchestration, &u.Reason, &u.Model, &u.ModelCalls,
&u.PromptTokens, &u.CompletionTokens, &u.TotalTokens, &u.CachedTokens,
- &u.ReasoningTokens, &createdAt, &updatedAt,
+ &u.CacheWriteTokens, &u.ReasoningTokens, &createdAt, &updatedAt,
); err != nil {
return nil, fmt.Errorf("扫描模型Token用量明细失败: %w", err)
}
diff --git a/internal/database/model_token_usage_test.go b/internal/database/model_token_usage_test.go
index 5fa1a09f..51b94aae 100644
--- a/internal/database/model_token_usage_test.go
+++ b/internal/database/model_token_usage_test.go
@@ -28,6 +28,7 @@ func TestModelTokenUsagePersistsFromUsageProcessDetail(t *testing.T) {
"totalTokens": 13,
"cachedTokens": 4,
"reasoningTokens": 1,
+ "cacheWriteTokens": 2,
}); err != nil {
t.Fatalf("AddProcessDetail: %v", err)
}
@@ -36,12 +37,15 @@ func TestModelTokenUsagePersistsFromUsageProcessDetail(t *testing.T) {
if err != nil {
t.Fatalf("GetModelTokenUsageStats: %v", err)
}
- if stats.Summary.Events != 1 || stats.Summary.ModelCalls != 2 || stats.Summary.TotalTokens != 13 || stats.Summary.CachedTokens != 4 || stats.Summary.ReasoningTokens != 1 {
+ if stats.Summary.Events != 1 || stats.Summary.ModelCalls != 2 || stats.Summary.TotalTokens != 13 || stats.Summary.CachedTokens != 4 || stats.Summary.ReasoningTokens != 1 || stats.Summary.CacheWriteTokens != 2 {
t.Fatalf("summary = %#v", stats.Summary)
}
- if len(stats.ByModel) != 1 || stats.ByModel[0].Key != "gpt-test" || stats.ByModel[0].TotalTokens != 13 {
+ if len(stats.ByModel) != 1 || stats.ByModel[0].Key != "gpt-test" || stats.ByModel[0].TotalTokens != 13 || stats.ByModel[0].CacheWriteTokens != 2 {
t.Fatalf("by model = %#v", stats.ByModel)
}
+ if len(stats.Recent) != 1 || stats.Recent[0].CacheWriteTokens != 2 || stats.Today.CacheWriteTokens != 2 || len(stats.ByDay) != 1 || stats.ByDay[0].CacheWriteTokens != 2 {
+ t.Fatalf("cache write usage lost: %#v", stats)
+ }
}
func TestModelTokenUsageBackfillIsIdempotent(t *testing.T) {
@@ -83,3 +87,36 @@ func newModelTokenUsageTestDB(t *testing.T) *DB {
t.Cleanup(func() { _ = db.Close() })
return db
}
+
+func TestModelTokenUsageStatsRespectConversationAccess(t *testing.T) {
+ db := newModelTokenUsageTestDB(t)
+ var ownID string
+ for _, owner := range []string{"alice", "bob"} {
+ conv, err := db.CreateConversation(owner, ConversationCreateMeta{})
+ if err != nil {
+ t.Fatal(err)
+ }
+ if owner == "alice" {
+ ownID = conv.ID
+ }
+ if _, err := db.Exec(`UPDATE conversations SET owner_user_id = ? WHERE id = ?`, owner, conv.ID); err != nil {
+ t.Fatal(err)
+ }
+ msg, err := db.AddMessage(conv.ID, "assistant", "done", nil)
+ if err != nil {
+ t.Fatal(err)
+ }
+ if err := db.AddProcessDetail(msg.ID, conv.ID, modelTokenUsageEventType, "usage", map[string]interface{}{
+ "model": owner, "modelCalls": 1, "promptTokens": 100, "completionTokens": 20, "cacheWriteTokens": 30,
+ }); err != nil {
+ t.Fatal(err)
+ }
+ }
+ stats, err := db.GetModelTokenUsageStats(ModelTokenUsageFilter{Access: RBACListAccess{UserID: "alice", Scope: "own"}})
+ if err != nil {
+ t.Fatal(err)
+ }
+ if stats.Summary.Events != 1 || stats.Summary.TotalTokens != 120 || stats.Summary.CacheWriteTokens != 30 || len(stats.Recent) != 1 || stats.Recent[0].ConversationID != ownID || len(stats.ByModel) != 1 || stats.ByModel[0].Key != "alice" {
+ t.Fatalf("usage leaks across users: %#v", stats)
+ }
+}
diff --git a/internal/database/schema_reconcile_test.go b/internal/database/schema_reconcile_test.go
index 3ed2cd01..9c346e94 100644
--- a/internal/database/schema_reconcile_test.go
+++ b/internal/database/schema_reconcile_test.go
@@ -115,6 +115,7 @@ func TestStartupRepairsTablesAndUnlistedColumnsPreservesData(t *testing.T) {
ALTER TABLE hitl_interrupts DROP COLUMN payload;
ALTER TABLE hitl_conversation_configs DROP COLUMN reviewer;
ALTER TABLE model_token_usage DROP COLUMN cached_tokens;
+ ALTER TABLE model_token_usage DROP COLUMN cache_write_tokens;
ALTER TABLE rbac_users DROP COLUMN display_name;
ALTER TABLE messages DROP COLUMN reasoning_content;`)
db.Close()
diff --git a/internal/database/schemas/application.sql b/internal/database/schemas/application.sql
index 2bba4c23..33754916 100644
--- a/internal/database/schemas/application.sql
+++ b/internal/database/schemas/application.sql
@@ -321,6 +321,7 @@ CREATE TABLE model_token_usage (
completion_tokens INTEGER NOT NULL DEFAULT 0,
total_tokens INTEGER NOT NULL DEFAULT 0,
cached_tokens INTEGER NOT NULL DEFAULT 0,
+ cache_write_tokens INTEGER NOT NULL DEFAULT 0,
reasoning_tokens INTEGER NOT NULL DEFAULT 0,
created_at DATETIME NOT NULL,
updated_at DATETIME NOT NULL,
diff --git a/internal/multiagent/eino_run_usage_accumulator.go b/internal/multiagent/eino_run_usage_accumulator.go
index 1cc06cc7..5c468440 100644
--- a/internal/multiagent/eino_run_usage_accumulator.go
+++ b/internal/multiagent/eino_run_usage_accumulator.go
@@ -13,6 +13,7 @@ type einoRunUsageSummary struct {
CompletionTokens int
TotalTokens int
CachedTokens int
+ CacheWriteTokens int
ReasoningTokens int
}
@@ -42,8 +43,13 @@ func (a *einoRunUsageAccumulator) AddUsage(usage *schema.TokenUsage) bool {
a.summary.ModelCalls++
a.summary.PromptTokens += usage.PromptTokens
a.summary.CompletionTokens += usage.CompletionTokens
- a.summary.TotalTokens += usage.TotalTokens
+ total := usage.TotalTokens
+ if total == 0 {
+ total = usage.PromptTokens + usage.CompletionTokens
+ }
+ a.summary.TotalTokens += total
a.summary.CachedTokens += usage.PromptTokenDetails.CachedTokens
+ a.summary.CacheWriteTokens += usage.PromptTokenDetails.CacheWriteTokens
a.summary.ReasoningTokens += usage.CompletionTokensDetails.ReasoningTokens
return true
}
@@ -88,6 +94,7 @@ func (a *einoRunUsageAccumulator) EmitOnce(
"completionTokens": s.CompletionTokens,
"totalTokens": s.TotalTokens,
"cachedTokens": s.CachedTokens,
+ "cacheWriteTokens": s.CacheWriteTokens,
"reasoningTokens": s.ReasoningTokens,
}
if progress != nil {
@@ -104,6 +111,7 @@ func (a *einoRunUsageAccumulator) EmitOnce(
zap.Int("completionTokens", s.CompletionTokens),
zap.Int("totalTokens", s.TotalTokens),
zap.Int("cachedTokens", s.CachedTokens),
+ zap.Int("cacheWriteTokens", s.CacheWriteTokens),
zap.Int("reasoningTokens", s.ReasoningTokens),
)
}
@@ -129,6 +137,9 @@ func maxEinoTokenUsage(dst *schema.TokenUsage, src *schema.TokenUsage) *schema.T
if src.PromptTokenDetails.CachedTokens > dst.PromptTokenDetails.CachedTokens {
dst.PromptTokenDetails.CachedTokens = src.PromptTokenDetails.CachedTokens
}
+ if src.PromptTokenDetails.CacheWriteTokens > dst.PromptTokenDetails.CacheWriteTokens {
+ dst.PromptTokenDetails.CacheWriteTokens = src.PromptTokenDetails.CacheWriteTokens
+ }
if src.CompletionTokensDetails.ReasoningTokens > dst.CompletionTokensDetails.ReasoningTokens {
dst.CompletionTokensDetails.ReasoningTokens = src.CompletionTokensDetails.ReasoningTokens
}
@@ -149,5 +160,6 @@ func tokenUsageEmpty(u *schema.TokenUsage) bool {
u.CompletionTokens == 0 &&
u.TotalTokens == 0 &&
u.PromptTokenDetails.CachedTokens == 0 &&
+ u.PromptTokenDetails.CacheWriteTokens == 0 &&
u.CompletionTokensDetails.ReasoningTokens == 0)
}
diff --git a/internal/multiagent/eino_run_usage_accumulator_test.go b/internal/multiagent/eino_run_usage_accumulator_test.go
index a26e3c3b..374c04a2 100644
--- a/internal/multiagent/eino_run_usage_accumulator_test.go
+++ b/internal/multiagent/eino_run_usage_accumulator_test.go
@@ -79,3 +79,25 @@ func TestMaxEinoTokenUsageUsesLargestStreamChunkValues(t *testing.T) {
t.Fatalf("usage = %#v", got)
}
}
+
+func TestEinoRunUsageCacheWriteDoesNotInflateTotal(t *testing.T) {
+ acc := newEinoRunUsageAccumulator()
+ var stream *schema.TokenUsage
+ for i := 0; i < 2; i++ {
+ stream = maxEinoTokenUsage(stream, &schema.TokenUsage{
+ PromptTokens: 100, CompletionTokens: 20,
+ PromptTokenDetails: schema.PromptTokenDetails{CachedTokens: 40, CacheWriteTokens: 30},
+ CompletionTokensDetails: schema.CompletionTokensDetails{ReasoningTokens: 10},
+ })
+ }
+ acc.AddUsage(stream)
+ got := acc.Summary()
+ if got.ModelCalls != 1 || got.TotalTokens != 120 || got.CacheWriteTokens != 30 || got.CachedTokens != 40 || got.ReasoningTokens != 10 {
+ t.Fatalf("summary = %#v", got)
+ }
+ var emitted map[string]interface{}
+ acc.EmitOnce("conv", "deep", "final", "claude-test", func(_, _ string, data interface{}) { emitted = data.(map[string]interface{}) }, nil)
+ if emitted["cacheWriteTokens"] != 30 || emitted["totalTokens"] != 120 {
+ t.Fatalf("event = %#v", emitted)
+ }
+}
diff --git a/internal/openai/eino_http.go b/internal/openai/eino_http.go
index a4d761e0..625da8ac 100644
--- a/internal/openai/eino_http.go
+++ b/internal/openai/eino_http.go
@@ -21,6 +21,7 @@ func NewEinoHTTPClient(cfg *config.OpenAIConfig, base *http.Client) *http.Client
transport = &reasoningToolChoiceCompatRoundTripper{base: transport, cfg: cfg}
transport = &einoSSEErrorRoundTripper{base: transport}
transport = &einoSSESanitizingRoundTripper{base: transport}
+ transport = &einoUsageNormalizingRoundTripper{base: transport}
cloned.Transport = transport
return &cloned
}
diff --git a/internal/openai/eino_sse_sanitizer.go b/internal/openai/eino_sse_sanitizer.go
index 340b3a04..6f6319c2 100644
--- a/internal/openai/eino_sse_sanitizer.go
+++ b/internal/openai/eino_sse_sanitizer.go
@@ -19,7 +19,7 @@ package openai
//
// 该层对调用方完全透明:
// - 仅当响应 Content-Type 是 text/event-stream 时介入;普通 JSON 响应原样透传
-// - data: payload (含 [DONE] 与 {"error":...}) 一字节不改
+// - data: payload 仅补齐 DeepSeek 缓存用量字段,其余内容原样透传
// - 上游真断流 (EOF / connection reset / context cancel) 原样透传
import (
@@ -103,6 +103,11 @@ func (b *einoSSESanitizingBody) Read(p []byte) (int, error) {
if line[len(line)-1] != '\n' {
line = append(line, '\n')
}
+ payload := bytes.TrimSpace(bytes.TrimLeft(line, " \t")[5:])
+ normalized := normalizeEinoUsagePayload(payload)
+ if !bytes.Equal(payload, normalized) {
+ line = append(append([]byte("data: "), normalized...), '\n')
+ }
b.pending = line
if err != nil {
b.err = err
diff --git a/internal/openai/eino_usage_normalizer.go b/internal/openai/eino_usage_normalizer.go
new file mode 100644
index 00000000..0b14bc3b
--- /dev/null
+++ b/internal/openai/eino_usage_normalizer.go
@@ -0,0 +1,90 @@
+package openai
+
+import (
+ "bytes"
+ "encoding/json"
+ "io"
+ "net/http"
+ "strings"
+)
+
+// normalizeEinoUsagePayload bridges DeepSeek's cache counters to the OpenAI
+// details understood by Eino. Standard provider fields always take precedence.
+func normalizeEinoUsagePayload(payload []byte) []byte {
+ if !bytes.Contains(payload, []byte(`"prompt_cache_hit_tokens"`)) {
+ return payload
+ }
+ var root map[string]json.RawMessage
+ if json.Unmarshal(payload, &root) != nil {
+ return payload
+ }
+ var usage map[string]json.RawMessage
+ if json.Unmarshal(root["usage"], &usage) != nil {
+ return payload
+ }
+ hit, ok := usage["prompt_cache_hit_tokens"]
+ if !ok {
+ return payload
+ }
+ var count int64
+ if json.Unmarshal(hit, &count) != nil || count < 0 {
+ return payload
+ }
+ details := map[string]json.RawMessage{}
+ if raw := usage["prompt_tokens_details"]; len(raw) > 0 && string(raw) != "null" {
+ if json.Unmarshal(raw, &details) != nil {
+ return payload
+ }
+ }
+ if _, exists := details["cached_tokens"]; exists {
+ return payload
+ }
+ details["cached_tokens"] = hit
+ usage["prompt_tokens_details"], _ = json.Marshal(details)
+ root["usage"], _ = json.Marshal(usage)
+ out, err := json.Marshal(root)
+ if err != nil {
+ return payload
+ }
+ return out
+}
+
+// JSON responses are normalized lazily so RoundTrip retains its normal timing.
+// Streaming responses are normalized one data line at a time by the SSE reader.
+type einoUsageNormalizingRoundTripper struct{ base http.RoundTripper }
+
+func (rt *einoUsageNormalizingRoundTripper) RoundTrip(req *http.Request) (*http.Response, error) {
+ resp, err := rt.base.RoundTrip(req)
+ if err == nil && resp != nil && resp.Body != nil && resp.StatusCode == http.StatusOK && strings.HasPrefix(strings.ToLower(resp.Header.Get("Content-Type")), "application/json") {
+ resp.Body = &einoUsageJSONBody{upstream: resp.Body}
+ resp.ContentLength = -1
+ resp.Header.Del("Content-Length")
+ }
+ return resp, err
+}
+
+type einoUsageJSONBody struct {
+ upstream io.ReadCloser
+ reader *bytes.Reader
+ err error
+}
+
+func (b *einoUsageJSONBody) Read(p []byte) (int, error) {
+ if len(p) == 0 {
+ return 0, nil
+ }
+ if b.reader == nil {
+ raw, err := io.ReadAll(b.upstream)
+ b.err = err
+ if err == nil {
+ raw = normalizeEinoUsagePayload(raw)
+ }
+ b.reader = bytes.NewReader(raw)
+ }
+ n, err := b.reader.Read(p)
+ if err == io.EOF && b.err != nil {
+ return n, b.err
+ }
+ return n, err
+}
+func (b *einoUsageJSONBody) Close() error { return b.upstream.Close() }
diff --git a/internal/openai/eino_usage_normalizer_test.go b/internal/openai/eino_usage_normalizer_test.go
new file mode 100644
index 00000000..4bd319f9
--- /dev/null
+++ b/internal/openai/eino_usage_normalizer_test.go
@@ -0,0 +1,70 @@
+package openai
+
+import (
+ "encoding/json"
+ "io"
+ "net/http"
+ "strings"
+ "testing"
+)
+
+func TestNormalizeEinoDeepSeekCacheUsage(t *testing.T) {
+ for _, raw := range []string{
+ `{"id":9007199254740993,"usage":{"prompt_tokens":100,"prompt_cache_hit_tokens":80,"prompt_cache_miss_tokens":20}}`,
+ `{"usage":{"prompt_tokens_details":null,"prompt_cache_hit_tokens":80}}`,
+ } {
+ out := normalizeEinoUsagePayload([]byte(raw))
+ var root map[string]json.RawMessage
+ if err := json.Unmarshal(out, &root); err != nil {
+ t.Fatal(err)
+ }
+ var usage struct {
+ Details struct {
+ Cached int `json:"cached_tokens"`
+ } `json:"prompt_tokens_details"`
+ }
+ if err := json.Unmarshal(root["usage"], &usage); err != nil || usage.Details.Cached != 80 {
+ t.Fatalf("normalized = %s, err = %v", out, err)
+ }
+ if id := root["id"]; id != nil && string(id) != "9007199254740993" {
+ t.Fatalf("ID precision lost: %s", id)
+ }
+ }
+ for _, raw := range []string{
+ `[DONE]`, `{"error":{"message":"failed"}}`, `{"usage":{"prompt_cache_hit_tokens":-1}}`,
+ `{"usage":{"prompt_cache_hit_tokens":80,"prompt_tokens_details":{"cached_tokens":0}}}`,
+ } {
+ if out := string(normalizeEinoUsagePayload([]byte(raw))); out != raw {
+ t.Fatalf("unexpected change: %s", out)
+ }
+ }
+}
+
+func TestEinoDeepSeekCacheUsageJSONAndStream(t *testing.T) {
+ payload := `{"usage":{"prompt_tokens":100,"completion_tokens":5,"total_tokens":105,"prompt_cache_hit_tokens":80}}`
+ for _, stream := range []bool{false, true} {
+ contentType, body := "application/json", payload
+ if stream {
+ contentType, body = "text/event-stream", ": ping\ndata: "+payload+"\n\ndata: [DONE]\n"
+ }
+ client := NewEinoHTTPClient(nil, &http.Client{Transport: usageTestTransport(func(req *http.Request) (*http.Response, error) {
+ return &http.Response{StatusCode: 200, Header: http.Header{"Content-Type": []string{contentType}}, Body: io.NopCloser(strings.NewReader(body))}, nil
+ })})
+ resp, err := client.Get("http://example.invalid/v1/chat/completions")
+ if err != nil {
+ t.Fatal(err)
+ }
+ out, err := io.ReadAll(resp.Body)
+ resp.Body.Close()
+ if err != nil || !strings.Contains(string(out), `"cached_tokens":80`) {
+ t.Fatalf("stream=%v body=%s err=%v", stream, out, err)
+ }
+ if stream && !strings.Contains(string(out), "data: [DONE]") {
+ t.Fatal("lost stream terminator")
+ }
+ }
+}
+
+type usageTestTransport func(*http.Request) (*http.Response, error)
+
+func (f usageTestTransport) RoundTrip(req *http.Request) (*http.Response, error) { return f(req) }
diff --git a/web/static/css/style.css b/web/static/css/style.css
index 5e80d17f..100b2dd9 100644
--- a/web/static/css/style.css
+++ b/web/static/css/style.css
@@ -47219,3 +47219,25 @@ html[data-theme="dark"] { --tool-blocked-color: #f4bc62; }
.update-adopt-confirm-btn {
align-self: flex-start;
}
+
+/* Provider-reported token analysis, scoped by the dashboard project selector. */
+.token-usage-panel { margin-bottom: 20px; padding: 18px 22px; }
+.token-usage-panel > summary { cursor: pointer; }
+.token-usage-toolbar { display: flex; align-items: center; gap: 12px; margin-top: 18px; }
+.token-usage-toolbar select { padding: 6px 10px; border: 1px solid var(--border-color, #dce2ea); border-radius: 6px; background: var(--bg-secondary, #fff); color: inherit; }
+.token-usage-note { opacity: .72; font-size: 12px; line-height: 1.7; margin: 14px 0; }
+.token-usage-metrics { display: grid; grid-template-columns: repeat(4, minmax(0, 1fr)); gap: 10px; }
+.token-usage-metrics > div { padding: 12px; border: 1px solid var(--border-color, #dce2ea); border-radius: 8px; min-width: 0; }
+.token-usage-metrics span { display: block; font-size: 12px; opacity: .7; }
+.token-usage-metrics strong { display: block; margin-top: 6px; font-size: 20px; overflow-wrap: anywhere; font-variant-numeric: tabular-nums; }
+.token-usage-table-wrap { overflow-x: auto; }
+.token-usage-table-wrap table { width: 100%; border-collapse: collapse; font-size: 12px; font-variant-numeric: tabular-nums; }
+.token-usage-table-wrap th, .token-usage-table-wrap td { padding: 10px; text-align: right; border-bottom: 1px solid var(--border-color, #dce2ea); white-space: nowrap; }
+.token-usage-table-wrap th:first-child, .token-usage-table-wrap td:first-child { text-align: left; }
+.token-usage-table-wrap td:first-child { max-width: 280px; overflow: hidden; text-overflow: ellipsis; }
+@media (max-width: 640px) { .token-usage-metrics { grid-template-columns: repeat(2, minmax(0, 1fr)); } .token-usage-panel { padding: 14px; } }
+.token-usage-trend { display: flex; align-items: flex-end; gap: 8px; overflow-x: auto; padding: 12px 0; }
+.token-usage-day { display: flex; flex-direction: column; align-items: center; justify-content: flex-end; flex: 1 0 38px; height: 128px; gap: 6px; font-size: 11px; }
+.token-usage-day-bar { width: 70%; max-width: 48px; background: var(--accent-color, #3b82f6); border-radius: 4px 4px 0 0; }
+
+.token-usage-panel h4 { margin: 20px 0 8px; }
diff --git a/web/static/i18n/en-US.json b/web/static/i18n/en-US.json
index 14e72eb0..25c5a3c2 100644
--- a/web/static/i18n/en-US.json
+++ b/web/static/i18n/en-US.json
@@ -287,7 +287,7 @@
"toolCalls": "Tool invocations",
"successRate": "Tool success rate",
"tokenUsage": "Token usage",
- "tokenUsageSub": "Last 7 days {{calls}} calls · Today {{today}}",
+ "tokenUsageSub": "Last {{days}} days: {{calls}} calls · Today {{today}}",
"noTokenUsageYet": "No usage yet",
"clickToViewTasks": "Click to view tasks",
"clickToViewChat": "Click to view conversations",
@@ -433,7 +433,33 @@
"mcpPartialDown_other": "{{count}} stopped",
"mcpAllDown": "All stopped",
"noVulnDesc": "This list shows recent records; new results appear here when detection completes in chat",
- "startScanBtn": "Go to chat to scan"
+ "startScanBtn": "Go to chat to scan",
+ "usageView": "View token usage",
+ "usagePeriod": "Period",
+ "usage7Days": "Last 7 days",
+ "usage30Days": "Last 30 days",
+ "usage90Days": "Last 90 days",
+ "usageTotal": "Total tokens",
+ "usageInput": "Input tokens",
+ "usageOutput": "Output tokens",
+ "usageCacheRead": "Cache read",
+ "usageCacheWrite": "Cache write",
+ "usageReasoning": "Reasoning tokens",
+ "usageCalls": "Model calls",
+ "usageCacheRate": "Cache read / input",
+ "usageByModel": "Usage by model (up to 20)",
+ "usageByDay": "Daily usage",
+ "usageRecent": "Recent runs (up to 20)",
+ "usageDate": "Date",
+ "usageTime": "Time",
+ "usageModel": "Model",
+ "usageStatus": "End reason",
+ "usageUnavailable": "Token usage is unavailable",
+ "usageScope": "Provider-reported usage from recorded Agent runs, including sub-agents. Cache reads and writes are part of input; reasoning is part of output. These details are not added to totals again. Unreported or uncollected usage is excluded. This is not a provider bill. Models are grouped by run configuration; runs with model failover may contain mixed usage.",
+ "usageShare": "Token share",
+ "usageTrend": "Daily token trend",
+ "usageFinal": "Completed",
+ "usagePartial": "Partial usage"
},
"projects": {
"title": "Projects",
@@ -795,7 +821,7 @@
"turnDurationHours": "{{hours}} hr {{minutes}} min",
"turnProcessAria": "{{state}}; expand or collapse execution details",
"turnTokenUsageLabel": "{{tokens}} tokens",
- "turnTokenUsageTitle": "Token usage: {{total}} (input {{prompt}}, output {{completion}}, cached {{cached}}, reasoning {{reasoning}}, {{calls}} calls)",
+ "turnTokenUsageTitle": "Token usage: {{total}} (input {{prompt}}, output {{completion}}, cached {{cached}}, reasoning {{reasoning}}, {{calls}} calls) · Cache write {{cacheWrite}}",
"turnNumber": "Turn {{number}}",
"turnPending": "Processing…",
"expandDetailLazyHint": "Expand details (loads iteration details on click)",
@@ -979,7 +1005,8 @@
"hitlTimeoutUnlimited": "No limit",
"hitlTimeoutHint": "Unanswered requests are rejected automatically when time expires; approval cards show the countdown.",
"hitlStatusOff": "Human-in-the-loop: Off",
- "rolePanelTitle": "Select role"
+ "rolePanelTitle": "Select role",
+ "einoUsageCacheWriteTokens": "Cache write tokens"
},
"toolGuard": {
"invalidTestResponse": "The server returned an invalid test result",
@@ -3722,7 +3749,6 @@
"hitlPolicy": "Tool approval",
"hitlHint": "Applies to all tasks in this queue, including tasks added later. Uses the global whitelist, audit strategy and timeout.",
"hitlSubtaskHint": "New tasks use the queue’s tool approval setting. Change it in queue details.",
-
"title": "New task",
"queueTitle": "Queue title",
"queueTitlePlaceholder": "Enter queue title (optional, for identification and filtering)",
diff --git a/web/static/i18n/ru-RU.json b/web/static/i18n/ru-RU.json
index 02370429..25c0928d 100644
--- a/web/static/i18n/ru-RU.json
+++ b/web/static/i18n/ru-RU.json
@@ -287,7 +287,7 @@
"toolCalls": "Вызовы инструментов",
"successRate": "Успешность инструментов",
"tokenUsage": "Расход токенов",
- "tokenUsageSub": "За 7 дней {{calls}} вызовов · сегодня {{today}}",
+ "tokenUsageSub": "За {{days}} дней {{calls}} вызовов · сегодня {{today}}",
"noTokenUsageYet": "Расхода пока нет",
"clickToViewTasks": "Открыть задачи",
"clickToViewChat": "Открыть диалоги",
@@ -445,7 +445,33 @@
"recoApproveHitl": "Одобрить запросы HITL: {{count}}",
"recoRestartMcp": "Проверить не запущенные внешние MCP: {{count}}",
"recoCheckMonitor": "Разобрать неудачные вызовы инструментов: {{count}}",
- "mcpPartialDown": "Не запущено: {{count}}"
+ "mcpPartialDown": "Не запущено: {{count}}",
+ "usageView": "Расход токенов",
+ "usagePeriod": "Период",
+ "usage7Days": "За 7 дней",
+ "usage30Days": "За 30 дней",
+ "usage90Days": "За 90 дней",
+ "usageTotal": "Всего токенов",
+ "usageInput": "Входные токены",
+ "usageOutput": "Выходные токены",
+ "usageCacheRead": "Чтение кэша",
+ "usageCacheWrite": "Запись кэша",
+ "usageReasoning": "Токены рассуждения",
+ "usageCalls": "Вызовы модели",
+ "usageCacheRate": "Чтение кэша / ввод",
+ "usageByModel": "По моделям (до 20)",
+ "usageByDay": "По дням",
+ "usageRecent": "Последние запуски (до 20)",
+ "usageDate": "Дата",
+ "usageTime": "Время",
+ "usageModel": "Модель",
+ "usageStatus": "Причина завершения",
+ "usageUnavailable": "Статистика недоступна",
+ "usageShare": "Доля токенов",
+ "usageTrend": "Расход по дням",
+ "usageScope": "Данные провайдера из сохранённых запусков Agent, включая субагентов. Чтение и запись кэша входят во ввод, рассуждение — в вывод; они не прибавляются к сумме повторно. Неполученные данные исключены. Это не счёт провайдера. Группировка по модели в конфигурации запуска; при переключении модели расход может быть смешан.",
+ "usageFinal": "Завершено",
+ "usagePartial": "Частичный расход"
},
"projects": {
"title": "Проекты",
@@ -807,7 +833,7 @@
"turnDurationHours": "{{hours}} ч {{minutes}} мин",
"turnProcessAria": "{{state}}; развернуть или свернуть подробности выполнения",
"turnTokenUsageLabel": "{{tokens}} токенов",
- "turnTokenUsageTitle": "Расход токенов: {{total}} (ввод {{prompt}}, вывод {{completion}}, кэш {{cached}}, рассуждение {{reasoning}}, вызовов {{calls}})",
+ "turnTokenUsageTitle": "Расход токенов: {{total}} (ввод {{prompt}}, вывод {{completion}}, кэш {{cached}}, рассуждение {{reasoning}}, вызовов {{calls}}) · Запись кэша {{cacheWrite}}",
"turnNumber": "Ход {{number}}",
"turnPending": "Обработка…",
"expandDetailLazyHint": "Развернуть подробности (итерации загружаются по щелчку)",
@@ -991,7 +1017,8 @@
"hitlTimeoutUnlimited": "Без ограничения",
"hitlTimeoutHint": "Запросы без ответа автоматически отклоняются по истечении времени; на карточках одобрения виден отсчёт.",
"hitlStatusOff": "Контроль человеком: выкл.",
- "rolePanelTitle": "Выбор роли"
+ "rolePanelTitle": "Выбор роли",
+ "einoUsageCacheWriteTokens": "Токены записи кэша"
},
"toolGuard": {
"invalidTestResponse": "Сервер вернул некорректный результат проверки",
diff --git a/web/static/i18n/zh-CN.json b/web/static/i18n/zh-CN.json
index 6cf0dd9a..00f8d90e 100644
--- a/web/static/i18n/zh-CN.json
+++ b/web/static/i18n/zh-CN.json
@@ -287,7 +287,7 @@
"toolCalls": "工具调用次数",
"successRate": "工具执行成功率",
"tokenUsage": "Token 用量",
- "tokenUsageSub": "近 7 天 {{calls}} 次调用 · 今日 {{today}}",
+ "tokenUsageSub": "近 {{days}} 天 {{calls}} 次调用 · 今日 {{today}}",
"noTokenUsageYet": "暂无用量",
"clickToViewTasks": "点击查看任务管理",
"clickToViewChat": "点击查看对话",
@@ -421,7 +421,33 @@
"mcpPartialDown": "{{count}} 个未运行",
"mcpAllDown": "全部未运行",
"noVulnDesc": "此处展示近期漏洞记录;在对话中完成检测后,新结果会出现在这里",
- "startScanBtn": "前往对话发起扫描"
+ "startScanBtn": "前往对话发起扫描",
+ "usageView": "查看用量详情",
+ "usagePeriod": "统计周期",
+ "usage7Days": "近 7 天",
+ "usage30Days": "近 30 天",
+ "usage90Days": "近 90 天",
+ "usageTotal": "总 Token",
+ "usageInput": "输入 Token",
+ "usageOutput": "输出 Token",
+ "usageCacheRead": "缓存读取",
+ "usageCacheWrite": "缓存写入",
+ "usageReasoning": "推理 Token",
+ "usageCalls": "模型调用",
+ "usageCacheRate": "缓存读取占输入",
+ "usageByModel": "模型用量(最多 20 项)",
+ "usageByDay": "每日用量",
+ "usageRecent": "最近运行(最多 20 项)",
+ "usageDate": "日期",
+ "usageTime": "时间",
+ "usageModel": "模型",
+ "usageStatus": "结束原因",
+ "usageUnavailable": "用量统计暂不可用",
+ "usageScope": "统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。 模型按运行配置归类,切换模型的运行可能混合用量。",
+ "usageShare": "用量占比",
+ "usageTrend": "每日用量趋势",
+ "usageFinal": "已完成",
+ "usagePartial": "部分用量"
},
"projects": {
"title": "项目管理",
@@ -783,7 +809,7 @@
"turnDurationHours": "{{hours}} 小时 {{minutes}} 分钟",
"turnProcessAria": "{{state}},展开或收起执行过程",
"turnTokenUsageLabel": "{{tokens}} tokens",
- "turnTokenUsageTitle": "Token 用量:{{total}}(输入 {{prompt}},输出 {{completion}},缓存 {{cached}},推理 {{reasoning}},调用 {{calls}} 次)",
+ "turnTokenUsageTitle": "Token 用量:{{total}}(输入 {{prompt}},输出 {{completion}},缓存 {{cached}},推理 {{reasoning}},调用 {{calls}} 次) · 缓存写入 {{cacheWrite}}",
"turnNumber": "第 {{number}} 轮",
"turnPending": "正在处理…",
"expandDetailLazyHint": "展开详情(点击后加载迭代详情)",
@@ -967,7 +993,8 @@
"hitlTimeoutUnlimited": "不限制",
"hitlTimeoutHint": "到期未处理将自动拒绝;审批卡片会显示倒计时。",
"hitlStatusOff": "人机协同:关闭",
- "rolePanelTitle": "选择角色"
+ "rolePanelTitle": "选择角色",
+ "einoUsageCacheWriteTokens": "缓存写入 tokens"
},
"toolGuard": {
"invalidTestResponse": "服务端返回的测试结果格式不正确",
@@ -3710,7 +3737,6 @@
"hitlPolicy": "工具审批",
"hitlHint": "队列内所有任务(含后续添加的任务)使用此设置;白名单、审计策略和等待时限沿用全局配置。",
"hitlSubtaskHint": "新增任务沿用队列的工具审批设置,可在队列详情中修改。",
-
"title": "新建任务",
"queueTitle": "任务标题",
"queueTitlePlaceholder": "请输入任务标题(可选,用于标识和筛选)",
diff --git a/web/static/js/chat-scroll-refresh.test.cjs b/web/static/js/chat-scroll-refresh.test.cjs
index 53cc6a75..24dfa94b 100644
--- a/web/static/js/chat-scroll-refresh.test.cjs
+++ b/web/static/js/chat-scroll-refresh.test.cjs
@@ -341,7 +341,7 @@ test('消息气泡内部流式增高时仅在跟随模式继续粘底', () => {
test('页面在任务补流脚本之前加载智能滚动控制器', () => {
const scrollIndex = html.indexOf('/static/js/chat-scroll.js?v=20260815-1');
- const monitorIndex = html.indexOf('/static/js/monitor.js?v=20260907-blocked-1');
+ const monitorIndex = html.indexOf('/static/js/monitor.js?v=20261011-token-usage');
assert.notEqual(scrollIndex, -1);
assert.notEqual(monitorIndex, -1);
diff --git a/web/static/js/chat.js b/web/static/js/chat.js
index 70637194..8d26bcdb 100644
--- a/web/static/js/chat.js
+++ b/web/static/js/chat.js
@@ -4945,6 +4945,7 @@ function normalizeAssistantTurnTokenUsage(data) {
completionTokens: assistantTurnUsageNumber(source.completionTokens),
totalTokens: assistantTurnUsageNumber(source.totalTokens),
cachedTokens: assistantTurnUsageNumber(source.cachedTokens),
+ cacheWriteTokens: assistantTurnUsageNumber(source.cacheWriteTokens),
reasoningTokens: assistantTurnUsageNumber(source.reasoningTokens),
model: source.model != null ? String(source.model).trim() : ''
};
@@ -4962,6 +4963,7 @@ function mergeAssistantTurnTokenUsage(target, usage) {
completionTokens: 0,
totalTokens: 0,
cachedTokens: 0,
+ cacheWriteTokens: 0,
reasoningTokens: 0,
model: ''
};
@@ -4970,6 +4972,7 @@ function mergeAssistantTurnTokenUsage(target, usage) {
out.completionTokens += usage.completionTokens || 0;
out.totalTokens += usage.totalTokens || 0;
out.cachedTokens += usage.cachedTokens || 0;
+ out.cacheWriteTokens += usage.cacheWriteTokens || 0;
out.reasoningTokens += usage.reasoningTokens || 0;
if (!out.model && usage.model) out.model = usage.model;
return out.totalTokens > 0 ? out : null;
@@ -4998,6 +5001,7 @@ function setAssistantTurnTokenUsage(messageElementOrId, usage) {
delete messageElement.dataset.turnCompletionTokens;
delete messageElement.dataset.turnTotalTokens;
delete messageElement.dataset.turnCachedTokens;
+ delete messageElement.dataset.turnCacheWriteTokens;
delete messageElement.dataset.turnReasoningTokens;
delete messageElement.dataset.turnModel;
syncAssistantTurnSummary(messageElement);
@@ -5008,6 +5012,7 @@ function setAssistantTurnTokenUsage(messageElementOrId, usage) {
messageElement.dataset.turnCompletionTokens = String(normalized.completionTokens || 0);
messageElement.dataset.turnTotalTokens = String(normalized.totalTokens || 0);
messageElement.dataset.turnCachedTokens = String(normalized.cachedTokens || 0);
+ messageElement.dataset.turnCacheWriteTokens = String(normalized.cacheWriteTokens || 0);
messageElement.dataset.turnReasoningTokens = String(normalized.reasoningTokens || 0);
if (normalized.model) {
messageElement.dataset.turnModel = normalized.model;
@@ -5025,6 +5030,7 @@ function getAssistantTurnTokenUsage(messageElement) {
completionTokens: messageElement.dataset.turnCompletionTokens,
totalTokens: messageElement.dataset.turnTotalTokens,
cachedTokens: messageElement.dataset.turnCachedTokens,
+ cacheWriteTokens: messageElement.dataset.turnCacheWriteTokens,
reasoningTokens: messageElement.dataset.turnReasoningTokens,
model: messageElement.dataset.turnModel
});
@@ -5051,6 +5057,7 @@ function formatAssistantTurnTokenUsageTitle(usage) {
prompt: formatAssistantTurnTokenCount(safeUsage.promptTokens),
completion: formatAssistantTurnTokenCount(safeUsage.completionTokens),
cached: formatAssistantTurnTokenCount(safeUsage.cachedTokens),
+ cacheWrite: formatAssistantTurnTokenCount(safeUsage.cacheWriteTokens),
reasoning: formatAssistantTurnTokenCount(safeUsage.reasoningTokens),
calls: formatAssistantTurnTokenCount(safeUsage.modelCalls),
model: safeUsage.model || ''
diff --git a/web/static/js/dashboard.js b/web/static/js/dashboard.js
index 23243bd5..e45a774a 100644
--- a/web/static/js/dashboard.js
+++ b/web/static/js/dashboard.js
@@ -17,6 +17,7 @@ var DASHBOARD_SEVERITY_STATUS_FILTER_STORAGE_KEY = 'cyberstrike.dashboard.severi
var DASHBOARD_SEVERITY_STATUS_FILTER_VALUES = ['', 'open', 'confirmed', 'fixed', 'ignored', 'false_positive'];
var dashboardState = {
+ tokenDays: 7,
currentController: null, // 当前正在进行的 fetch 的 AbortController
pollTimer: null, // 自动轮询的 setInterval id
staleTimer: null, // 过期检查的 setInterval id
@@ -162,7 +163,7 @@ async function refreshDashboard() {
fetchJson(dashboardProjectScopedUrl('/api/c2/tasks?page=1&page_size=1')),
fetchJson('/api/projects/dashboard-summary?fact_limit=10'),
selectedSeverityStatus ? fetchJson('/api/vulnerabilities/stats?status=' + encodeURIComponent(selectedSeverityStatus)) : Promise.resolve(null),
- fetchJson(dashboardProjectScopedUrl('/api/usage/tokens?days=7&limit=5'))
+ fetchJson(dashboardProjectScopedUrl('/api/usage/tokens?days=' + dashboardState.tokenDays + '&limit=20'))
]);
// 如果在 await 期间 controller 已被 abort,说明又有新刷新启动了,丢弃本次结果
@@ -440,6 +441,7 @@ async function refreshDashboard() {
setDashboardOverviewPlaceholder('-');
setEl('dashboard-kpi-success-rate', '-');
setEl('dashboard-kpi-tools-calls', '-');
+ renderDashboardTokenAnalysis(null);
setEl('dashboard-kpi-token-usage', '-');
setKpiSubText('dashboard-kpi-tasks-sub-text', '-');
setKpiSubText('dashboard-kpi-vuln-sub-text', '-');
@@ -708,6 +710,7 @@ function setKpiRateBadge(id, rate, failedCount) {
}
function renderDashboardTokenUsage(res) {
+ renderDashboardTokenAnalysis(res);
const summary = res && res.summary ? res.summary : null;
if (!summary) {
setEl('dashboard-kpi-token-usage', '-');
@@ -725,9 +728,10 @@ function renderDashboardTokenUsage(res) {
setEl('dashboard-kpi-token-usage', formatTokenUsageCompact(total));
setKpiSubText('dashboard-kpi-token-sub-text',
dt('dashboard.tokenUsageSub', {
+ days: dashboardState.tokenDays,
today: formatTokenUsageCompact(today),
calls: Number.isFinite(calls) ? calls : 0
- }, '近 7 天 ' + (Number.isFinite(calls) ? calls : 0) + ' 次调用 · 今日 ' + formatTokenUsageCompact(today)));
+ }, '近 ' + dashboardState.tokenDays + ' 天 ' + (Number.isFinite(calls) ? calls : 0) + ' 次调用 · 今日 ' + formatTokenUsageCompact(today)));
}
function formatTokenUsageCompact(num) {
@@ -2524,3 +2528,136 @@ document.addEventListener('click', function (ev) {
var banner = document.getElementById('dashboard-alert-banner');
if (banner) banner.hidden = true;
});
+
+function openDashboardTokenUsage() {
+ const panel = document.getElementById('dashboard-token-details');
+ if (!panel) return;
+ panel.open = true;
+ panel.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
+}
+
+function changeDashboardTokenPeriod(value) {
+ const days = Number(value);
+ if (![7, 30, 90].includes(days)) return;
+ dashboardState.tokenDays = days;
+ const host = document.getElementById('dashboard-token-analysis');
+ if (host) host.textContent = '…';
+ refreshDashboard();
+}
+
+function dashboardUsageCount(value) {
+ const n = Number(value);
+ return Number.isFinite(n) && n > 0 ? Math.trunc(n) : 0;
+}
+
+function dashboardUsageMetrics(summary) {
+ const input = dashboardUsageCount(summary.promptTokens);
+ const cached = dashboardUsageCount(summary.cachedTokens);
+ return [
+ ['usageTotal', summary.totalTokens],
+ ['usageInput', input],
+ ['usageOutput', summary.completionTokens],
+ ['usageCacheRead', cached],
+ ['usageCacheWrite', summary.cacheWriteTokens],
+ ['usageReasoning', summary.reasoningTokens],
+ ['usageCalls', summary.modelCalls],
+ ['usageCacheRate', input > 0 ? (Math.min(cached, input) / input * 100).toFixed(1) + '%' : '—']
+ ];
+}
+
+function renderDashboardTokenAnalysis(res) {
+ const host = document.getElementById('dashboard-token-analysis');
+ if (!host) return;
+ host.replaceChildren();
+ if (!res || !res.summary) {
+ host.textContent = dt('dashboard.usageUnavailable', null, '用量统计暂不可用');
+ return;
+ }
+ const exact = value => dashboardUsageCount(value).toLocaleString(window.__locale || 'zh-CN');
+ const label = key => dt('dashboard.' + key, null, key);
+ const metrics = document.createElement('div');
+ metrics.className = 'token-usage-metrics';
+ dashboardUsageMetrics(res.summary).forEach(([key, value]) => {
+ const card = document.createElement('div');
+ const title = document.createElement('span');
+ title.textContent = label(key);
+ const count = document.createElement('strong');
+ count.textContent = typeof value === 'string' ? value : exact(value);
+ card.append(title, count);
+ metrics.append(card);
+ });
+ host.append(metrics);
+ if (!dashboardUsageCount(res.summary.events)) {
+ const empty = document.createElement('p');
+ empty.textContent = dt('dashboard.noTokenUsageYet', null, '暂无用量');
+ host.append(empty);
+ return;
+ }
+ // Tables use text nodes: provider model names and conversation IDs are untrusted.
+ const table = (titleKey, headings, rows) => {
+ const section = document.createElement('section');
+ const title = document.createElement('h4');
+ title.textContent = label(titleKey);
+ const wrap = document.createElement('div');
+ wrap.className = 'token-usage-table-wrap';
+ const grid = document.createElement('table');
+ const caption = document.createElement('caption');
+ caption.className = 'sr-only';
+ caption.textContent = title.textContent;
+ const head = document.createElement('thead');
+ const hr = document.createElement('tr');
+ headings.forEach(key => {
+ const th = document.createElement('th');
+ th.scope = 'col';
+ th.textContent = label(key);
+ hr.append(th);
+ });
+ head.append(hr);
+ const body = document.createElement('tbody');
+ rows.forEach(values => {
+ const tr = document.createElement('tr');
+ values.forEach(value => {
+ const td = document.createElement('td');
+ td.textContent = String(value == null ? '' : value);
+ tr.append(td);
+ });
+ body.append(tr);
+ });
+ grid.append(caption, head, body);
+ wrap.append(grid);
+ section.append(title, wrap);
+ host.append(section);
+ };
+ const counts = row => [exact(row.promptTokens), exact(row.completionTokens), exact(row.cachedTokens),
+ exact(row.cacheWriteTokens), exact(row.reasoningTokens), exact(row.totalTokens), exact(row.modelCalls)];
+ const fields = ['usageInput', 'usageOutput', 'usageCacheRead', 'usageCacheWrite', 'usageReasoning', 'usageTotal', 'usageCalls'];
+ table('usageByModel', ['usageModel', 'usageShare', ...fields], (res.byModel || []).map(row => [row.label || row.key,
+ dashboardUsageCount(res.summary.totalTokens) > 0 ? (dashboardUsageCount(row.totalTokens) / dashboardUsageCount(res.summary.totalTokens) * 100).toFixed(1) + '%' : '—', ...counts(row)]));
+ const trendTitle = document.createElement('h4');
+ trendTitle.textContent = label('usageTrend');
+ const trend = document.createElement('div');
+ trend.className = 'token-usage-trend';
+ const days = (res.byDay || []).slice().reverse();
+ const peak = Math.max(1, ...days.map(row => dashboardUsageCount(row.totalTokens)));
+ days.forEach(row => {
+ const bar = document.createElement('div');
+ bar.className = 'token-usage-day';
+ const count = document.createElement('span');
+ count.textContent = formatTokenUsageCompact(row.totalTokens);
+ const fill = document.createElement('div');
+ fill.className = 'token-usage-day-bar';
+ fill.style.height = Math.max(1, dashboardUsageCount(row.totalTokens) / peak * 90) + 'px';
+ const date = document.createElement('span');
+ date.textContent = String(row.key || '').slice(5);
+ bar.title = row.key + ': ' + exact(row.totalTokens);
+ bar.append(count, fill, date);
+ trend.append(bar);
+ });
+ host.append(trendTitle, trend);
+ table('usageByDay', ['usageDate', ...fields], (res.byDay || []).map(row => [row.key, ...counts(row)]));
+ table('usageRecent', ['usageTime', 'usageModel', 'usageStatus', 'usageTotal', 'usageCalls'], (res.recent || []).map(row => {
+ const time = new Date(row.createdAt);
+ return [Number.isFinite(time.getTime()) ? time.toLocaleString(window.__locale || 'zh-CN') : '—',
+ row.model || '—', row.reason === 'final' ? label('usageFinal') : row.reason === 'partial' ? label('usagePartial') : (row.reason || '—'), exact(row.totalTokens), exact(row.modelCalls)];
+ }));
+}
diff --git a/web/static/js/hitl-approval-ui.test.cjs b/web/static/js/hitl-approval-ui.test.cjs
index 598bdf12..cf15377e 100644
--- a/web/static/js/hitl-approval-ui.test.cjs
+++ b/web/static/js/hitl-approval-ui.test.cjs
@@ -107,7 +107,7 @@ test('Agent 审查不进入人工审批弹窗、倒计时和项目计数', () =>
const hitlPage = fs.readFileSync('web/static/js/hitl.js', 'utf8');
assert.match(handler, /CreatePendingInterrupt\([\s\S]{0,260}reviewer string/);
assert.match(handler, /reviewer != "audit_agent"[\s\S]{0,120}m\.pending\[id\] = p/);
- assert.match(logsHandler, /ADD COLUMN reviewer TEXT NOT NULL DEFAULT 'human'/);
+ assert.match(fs.readFileSync('internal/database/schemas/application.sql', 'utf8'), /reviewer TEXT NOT NULL DEFAULT 'human'/);
assert.match(logsHandler, /status = 'pending' AND COALESCE\(reviewer,'human'\) = 'human'/);
assert.match(monitor, /function isAgentReviewedHitl\(data\)/);
assert.match(monitor, /if \(!data\.resolved && !isAgentReviewedHitl\(data\)\)/);
@@ -293,7 +293,7 @@ test('多对话并发时释放隐藏主流且旧请求不能覆盖新对话状
assert.match(chat, /let loadConversationAbortController = null/);
assert.match(chat, /cancelPendingConversationLoad\(\);[\s\S]{0,900}const conversationLoadController = new AbortController\(\)/);
assert.match(chat, /signal: conversationLoadController\.signal/);
- assert.match(template, /monitor\.js\?v=20260907-blocked-1/);
+ assert.match(template, /monitor\.js\?v=20261011-token-usage/);
assert.match(template, /chat-scroll\.js\?v=20260815-1/);
assert.match(template, /chat\.js\?v=[A-Za-z0-9._-]+/);
assert.match(template, /style\.css\?v=[A-Za-z0-9._-]+/);
diff --git a/web/static/js/monitor.js b/web/static/js/monitor.js
index 8009d489..aafad05c 100644
--- a/web/static/js/monitor.js
+++ b/web/static/js/monitor.js
@@ -2889,6 +2889,9 @@ function formatEinoUsageSummaryMessage(data) {
if (Number(d.cachedTokens || 0) > 0) {
rows.push([label('chat.einoUsageCachedTokens', '缓存 tokens'), d.cachedTokens]);
}
+ if (Number(d.cacheWriteTokens || 0) > 0) {
+ rows.push([label('chat.einoUsageCacheWriteTokens', '缓存写入 tokens'), d.cacheWriteTokens]);
+ }
if (Number(d.reasoningTokens || 0) > 0) {
rows.push([label('chat.einoUsageReasoningTokens', '推理 tokens'), d.reasoningTokens]);
}
@@ -6734,7 +6737,7 @@ function addTimelineItem(timeline, type, options) {
}
if (type === 'eino_usage_summary' && options.data) {
const d = options.data;
- ['modelCalls', 'promptTokens', 'completionTokens', 'totalTokens', 'cachedTokens', 'reasoningTokens'].forEach(function (key) {
+ ['modelCalls', 'promptTokens', 'completionTokens', 'totalTokens', 'cachedTokens', 'cacheWriteTokens', 'reasoningTokens'].forEach(function (key) {
if (d[key] != null) {
item.dataset[key] = String(d[key]);
}
@@ -9651,6 +9654,7 @@ function refreshProgressAndTimelineI18n() {
completionTokens: item.dataset.completionTokens,
totalTokens: item.dataset.totalTokens,
cachedTokens: item.dataset.cachedTokens,
+ cacheWriteTokens: item.dataset.cacheWriteTokens,
reasoningTokens: item.dataset.reasoningTokens
};
titleSpan.textContent = formatEinoUsageSummaryTitle(usageData);
diff --git a/web/static/js/token-usage-analysis.test.cjs b/web/static/js/token-usage-analysis.test.cjs
new file mode 100644
index 00000000..a6c61896
--- /dev/null
+++ b/web/static/js/token-usage-analysis.test.cjs
@@ -0,0 +1,43 @@
+const fs = require('node:fs');
+const vm = require('node:vm');
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const source = fs.readFileSync('web/static/js/dashboard.js', 'utf8');
+const harness = () => {
+ const context = { document: {}, dashboardState: { tokenDays: 7 }, refreshDashboard() {} };
+ vm.createContext(context);
+ vm.runInContext(source.slice(source.indexOf('function openDashboardTokenUsage()')), context);
+ return context;
+};
+
+test('cache and reasoning details do not inflate total or double-count input', () => {
+ const ctx = harness();
+ const metrics = ctx.dashboardUsageMetrics({ totalTokens: 120, promptTokens: 100, completionTokens: 20, cachedTokens: 40, cacheWriteTokens: 30, reasoningTokens: 10, modelCalls: 1 });
+ const values = Object.fromEntries(metrics);
+ assert.equal(values.usageTotal, 120);
+ assert.equal(values.usageCacheWrite, 30);
+ assert.equal(values.usageCacheRate, '40.0%');
+ assert.equal(Object.fromEntries(ctx.dashboardUsageMetrics({})).usageCacheRate, '—');
+ assert.equal(ctx.dashboardUsageCount(Infinity), 0);
+ assert.equal(ctx.dashboardUsageCount(-12), 0);
+});
+
+test('period selection refreshes once and rejects arbitrary periods', () => {
+ const ctx = harness();
+ let calls = 0;
+ ctx.refreshDashboard = () => { calls++; };
+ ctx.document.getElementById = () => ({ textContent: '' });
+ ctx.changeDashboardTokenPeriod('30');
+ ctx.changeDashboardTokenPeriod('999');
+ assert.equal(ctx.dashboardState.tokenDays, 30);
+ assert.equal(calls, 1);
+});
+
+test('all supported languages expose usage labels and interpolation placeholders', () => {
+ for (const locale of ['zh-CN', 'en-US', 'ru-RU']) {
+ const data = JSON.parse(fs.readFileSync(`web/static/i18n/${locale}.json`, 'utf8'));
+ for (const key of ['usageView', 'usageScope', 'usageCacheRead', 'usageCacheWrite', 'usageTrend']) assert.ok(data.dashboard[key]);
+ assert.match(data.dashboard.tokenUsageSub, /\{\{days\}\}/);
+ assert.match(data.chat.turnTokenUsageTitle, /\{\{cacheWrite\}\}/);
+ }
+});
diff --git a/web/static/js/turn-duration-refresh.test.cjs b/web/static/js/turn-duration-refresh.test.cjs
index 2f0d94b6..030128e2 100644
--- a/web/static/js/turn-duration-refresh.test.cjs
+++ b/web/static/js/turn-duration-refresh.test.cjs
@@ -117,12 +117,14 @@ test('助手轮次摘要会显示持久化 token 用量', () => {
promptTokens: 1200,
completionTokens: 34,
cachedTokens: 200,
+ cacheWriteTokens: 100,
reasoningTokens: 12,
modelCalls: 1,
model: 'deepseek-v3',
});
assert.equal(message.dataset.turnTotalTokens, '1234');
+ assert.equal(message.dataset.turnCacheWriteTokens, '100');
assert.match(message.label.innerHTML, /1\.2K tokens/);
assert.match(message.label.innerHTML, /turn-process-token-chip/);
});
diff --git a/web/static/js/webshell.js b/web/static/js/webshell.js
index 5999b317..b71e3e7c 100644
--- a/web/static/js/webshell.js
+++ b/web/static/js/webshell.js
@@ -2203,6 +2203,9 @@ function formatWebshellEinoUsageSummaryMessage(data) {
if (Number(d.cachedTokens || 0) > 0) {
rows.push([wsTOr('chat.einoUsageCachedTokens', '缓存 tokens'), d.cachedTokens]);
}
+ if (Number(d.cacheWriteTokens || 0) > 0) {
+ rows.push([wsTOr('chat.einoUsageCacheWriteTokens', '缓存写入 tokens'), d.cacheWriteTokens]);
+ }
if (Number(d.reasoningTokens || 0) > 0) {
rows.push([wsTOr('chat.einoUsageReasoningTokens', '推理 tokens'), d.reasoningTokens]);
}
diff --git a/web/templates/index.html b/web/templates/index.html
index 85ed32fb..3ced8a4a 100644
--- a/web/templates/index.html
+++ b/web/templates/index.html
@@ -556,7 +556,7 @@
运行平稳
-
+
Token 用量
@@ -567,6 +567,19 @@
+
+ 查看用量详情
+
+
+
+
+ 统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。模型按运行配置归类,切换模型的运行可能混合用量。
+
+
@@ -6996,10 +7009,10 @@
-
+
-
-
+
+
@@ -7016,7 +7029,7 @@
-
+
From 4eda42dc107511e70c54e7f6aeefbfba71fe3c67 Mon Sep 17 00:00:00 2001
From: Sycun <165354365+Sycun@users.noreply.github.com>
Date: Sun, 11 Oct 2026 23:51:01 +0800
Subject: [PATCH 2/5] feat: move token details to settings and show dashboard
cache hit rate
---
docs/zh-CN/token-usage-monitoring.md | 2 +-
web/static/css/style.css | 5 +-
web/static/i18n/en-US.json | 2 +
web/static/i18n/ru-RU.json | 2 +
web/static/i18n/zh-CN.json | 2 +
web/static/js/dashboard.js | 148 +--------------
web/static/js/router.js | 17 +-
web/static/js/settings.js | 12 ++
web/static/js/token-usage-analysis.test.cjs | 62 ++++--
web/static/js/token-usage.js | 197 ++++++++++++++++++++
web/static/js/update-ui.test.cjs | 2 +-
web/templates/index.html | 45 +++--
12 files changed, 320 insertions(+), 176 deletions(-)
create mode 100644 web/static/js/token-usage.js
diff --git a/docs/zh-CN/token-usage-monitoring.md b/docs/zh-CN/token-usage-monitoring.md
index f8c844b2..98247821 100644
--- a/docs/zh-CN/token-usage-monitoring.md
+++ b/docs/zh-CN/token-usage-monitoring.md
@@ -29,7 +29,7 @@ DeepSeek 的未命中输入不等于 Claude 的缓存写入。不能根据文本
## 功能入口与数据流
-点击首页「Token 用量」卡片或「查看用量详情」展开面板。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。沿用首页自动刷新和请求取消机制。
+点击首页「Token 用量」卡片进入「系统设置 → Token 用量」,也可直接从设置二级菜单打开。首页卡片显示近 7 天调用次数、今日用量与缓存命中率(缓存读取 Token / 输入 Token)。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。详情页独立加载,支持手动刷新与请求取消,切换周期不会刷新整个仪表盘;刷新页面可保持该设置分区。
运行事件 → 流式/非流式用量累加 → `eino_usage_summary` → `process_details` 与 `model_token_usage` → 现有 `/api/usage/tokens`、对话用量接口 → 首页与聊天摘要。
diff --git a/web/static/css/style.css b/web/static/css/style.css
index 100b2dd9..7b1576ac 100644
--- a/web/static/css/style.css
+++ b/web/static/css/style.css
@@ -47221,9 +47221,12 @@ html[data-theme="dark"] { --tool-blocked-color: #f4bc62; }
}
/* Provider-reported token analysis, scoped by the dashboard project selector. */
+.dashboard-kpi-sub--tokens { row-gap: 2px; }
+#dashboard-kpi-token-cache-text { flex-basis: 100%; }
.token-usage-panel { margin-bottom: 20px; padding: 18px 22px; }
-.token-usage-panel > summary { cursor: pointer; }
+.token-usage-header { display: flex; align-items: center; justify-content: space-between; gap: 12px; }
.token-usage-toolbar { display: flex; align-items: center; gap: 12px; margin-top: 18px; }
+.token-usage-toolbar label { white-space: nowrap; }
.token-usage-toolbar select { padding: 6px 10px; border: 1px solid var(--border-color, #dce2ea); border-radius: 6px; background: var(--bg-secondary, #fff); color: inherit; }
.token-usage-note { opacity: .72; font-size: 12px; line-height: 1.7; margin: 14px 0; }
.token-usage-metrics { display: grid; grid-template-columns: repeat(4, minmax(0, 1fr)); gap: 10px; }
diff --git a/web/static/i18n/en-US.json b/web/static/i18n/en-US.json
index 25c5a3c2..9f3f913c 100644
--- a/web/static/i18n/en-US.json
+++ b/web/static/i18n/en-US.json
@@ -287,6 +287,7 @@
"toolCalls": "Tool invocations",
"successRate": "Tool success rate",
"tokenUsage": "Token usage",
+ "usageCacheHitRate": "Cache hit {{rate}}",
"tokenUsageSub": "Last {{days}} days: {{calls}} calls · Today {{today}}",
"noTokenUsageYet": "No usage yet",
"clickToViewTasks": "Click to view tasks",
@@ -1969,6 +1970,7 @@
"settings": {
"title": "System settings",
"nav": {
+ "tokenUsage": "Token usage",
"basic": "Basic",
"hitl": "Human-in-the-loop",
"knowledge": "Knowledge base",
diff --git a/web/static/i18n/ru-RU.json b/web/static/i18n/ru-RU.json
index 25c0928d..667c550e 100644
--- a/web/static/i18n/ru-RU.json
+++ b/web/static/i18n/ru-RU.json
@@ -287,6 +287,7 @@
"toolCalls": "Вызовы инструментов",
"successRate": "Успешность инструментов",
"tokenUsage": "Расход токенов",
+ "usageCacheHitRate": "Попадания в кэш {{rate}}",
"tokenUsageSub": "За {{days}} дней {{calls}} вызовов · сегодня {{today}}",
"noTokenUsageYet": "Расхода пока нет",
"clickToViewTasks": "Открыть задачи",
@@ -1982,6 +1983,7 @@
"settings": {
"title": "Системные настройки",
"nav": {
+ "tokenUsage": "Расход токенов",
"basic": "Основные",
"hitl": "Человек в контуре",
"knowledge": "База знаний",
diff --git a/web/static/i18n/zh-CN.json b/web/static/i18n/zh-CN.json
index 00f8d90e..a758dbd3 100644
--- a/web/static/i18n/zh-CN.json
+++ b/web/static/i18n/zh-CN.json
@@ -287,6 +287,7 @@
"toolCalls": "工具调用次数",
"successRate": "工具执行成功率",
"tokenUsage": "Token 用量",
+ "usageCacheHitRate": "缓存命中 {{rate}}",
"tokenUsageSub": "近 {{days}} 天 {{calls}} 次调用 · 今日 {{today}}",
"noTokenUsageYet": "暂无用量",
"clickToViewTasks": "点击查看任务管理",
@@ -1957,6 +1958,7 @@
"settings": {
"title": "系统设置",
"nav": {
+ "tokenUsage": "Token 用量",
"basic": "基本设置",
"hitl": "人机协同",
"knowledge": "知识库",
diff --git a/web/static/js/dashboard.js b/web/static/js/dashboard.js
index e45a774a..eec890d3 100644
--- a/web/static/js/dashboard.js
+++ b/web/static/js/dashboard.js
@@ -17,7 +17,6 @@ var DASHBOARD_SEVERITY_STATUS_FILTER_STORAGE_KEY = 'cyberstrike.dashboard.severi
var DASHBOARD_SEVERITY_STATUS_FILTER_VALUES = ['', 'open', 'confirmed', 'fixed', 'ignored', 'false_positive'];
var dashboardState = {
- tokenDays: 7,
currentController: null, // 当前正在进行的 fetch 的 AbortController
pollTimer: null, // 自动轮询的 setInterval id
staleTimer: null, // 过期检查的 setInterval id
@@ -73,6 +72,7 @@ async function refreshDashboard() {
setKpiSubText('dashboard-kpi-tools-sub-text', '…');
setKpiSubText('dashboard-kpi-rate-sub-text', '…');
setKpiSubText('dashboard-kpi-token-sub-text', '…');
+ setKpiSubText('dashboard-kpi-token-cache-text', '…');
hideEl('dashboard-kpi-vuln-critical-badge');
hideEl('dashboard-alert-banner');
setRecentVulnsLoading();
@@ -163,7 +163,7 @@ async function refreshDashboard() {
fetchJson(dashboardProjectScopedUrl('/api/c2/tasks?page=1&page_size=1')),
fetchJson('/api/projects/dashboard-summary?fact_limit=10'),
selectedSeverityStatus ? fetchJson('/api/vulnerabilities/stats?status=' + encodeURIComponent(selectedSeverityStatus)) : Promise.resolve(null),
- fetchJson(dashboardProjectScopedUrl('/api/usage/tokens?days=' + dashboardState.tokenDays + '&limit=20'))
+ fetchJson(dashboardProjectScopedUrl('/api/usage/tokens?days=7&limit=20'))
]);
// 如果在 await 期间 controller 已被 abort,说明又有新刷新启动了,丢弃本次结果
@@ -441,8 +441,9 @@ async function refreshDashboard() {
setDashboardOverviewPlaceholder('-');
setEl('dashboard-kpi-success-rate', '-');
setEl('dashboard-kpi-tools-calls', '-');
- renderDashboardTokenAnalysis(null);
setEl('dashboard-kpi-token-usage', '-');
+ setKpiSubText('dashboard-kpi-token-sub-text', '-');
+ setKpiSubText('dashboard-kpi-token-cache-text', '-');
setKpiSubText('dashboard-kpi-tasks-sub-text', '-');
setKpiSubText('dashboard-kpi-vuln-sub-text', '-');
setKpiSubText('dashboard-kpi-tools-sub-text', '-');
@@ -710,13 +711,15 @@ function setKpiRateBadge(id, rate, failedCount) {
}
function renderDashboardTokenUsage(res) {
- renderDashboardTokenAnalysis(res);
const summary = res && res.summary ? res.summary : null;
if (!summary) {
setEl('dashboard-kpi-token-usage', '-');
setKpiSubText('dashboard-kpi-token-sub-text', '-');
+ setKpiSubText('dashboard-kpi-token-cache-text', '-');
return;
}
+ const cacheRate = tokenUsageCacheRate(summary);
+ setKpiSubText('dashboard-kpi-token-cache-text', dt('dashboard.usageCacheHitRate', { rate: cacheRate }, '缓存命中 ' + cacheRate));
const total = Number(summary.totalTokens || 0);
const calls = Number(summary.modelCalls || 0);
const today = res && res.today ? Number(res.today.totalTokens || 0) : 0;
@@ -728,10 +731,10 @@ function renderDashboardTokenUsage(res) {
setEl('dashboard-kpi-token-usage', formatTokenUsageCompact(total));
setKpiSubText('dashboard-kpi-token-sub-text',
dt('dashboard.tokenUsageSub', {
- days: dashboardState.tokenDays,
+ days: 7,
today: formatTokenUsageCompact(today),
calls: Number.isFinite(calls) ? calls : 0
- }, '近 ' + dashboardState.tokenDays + ' 天 ' + (Number.isFinite(calls) ? calls : 0) + ' 次调用 · 今日 ' + formatTokenUsageCompact(today)));
+ }, '近 7 天 ' + (Number.isFinite(calls) ? calls : 0) + ' 次调用 · 今日 ' + formatTokenUsageCompact(today)));
}
function formatTokenUsageCompact(num) {
@@ -2528,136 +2531,3 @@ document.addEventListener('click', function (ev) {
var banner = document.getElementById('dashboard-alert-banner');
if (banner) banner.hidden = true;
});
-
-function openDashboardTokenUsage() {
- const panel = document.getElementById('dashboard-token-details');
- if (!panel) return;
- panel.open = true;
- panel.scrollIntoView({ behavior: 'smooth', block: 'nearest' });
-}
-
-function changeDashboardTokenPeriod(value) {
- const days = Number(value);
- if (![7, 30, 90].includes(days)) return;
- dashboardState.tokenDays = days;
- const host = document.getElementById('dashboard-token-analysis');
- if (host) host.textContent = '…';
- refreshDashboard();
-}
-
-function dashboardUsageCount(value) {
- const n = Number(value);
- return Number.isFinite(n) && n > 0 ? Math.trunc(n) : 0;
-}
-
-function dashboardUsageMetrics(summary) {
- const input = dashboardUsageCount(summary.promptTokens);
- const cached = dashboardUsageCount(summary.cachedTokens);
- return [
- ['usageTotal', summary.totalTokens],
- ['usageInput', input],
- ['usageOutput', summary.completionTokens],
- ['usageCacheRead', cached],
- ['usageCacheWrite', summary.cacheWriteTokens],
- ['usageReasoning', summary.reasoningTokens],
- ['usageCalls', summary.modelCalls],
- ['usageCacheRate', input > 0 ? (Math.min(cached, input) / input * 100).toFixed(1) + '%' : '—']
- ];
-}
-
-function renderDashboardTokenAnalysis(res) {
- const host = document.getElementById('dashboard-token-analysis');
- if (!host) return;
- host.replaceChildren();
- if (!res || !res.summary) {
- host.textContent = dt('dashboard.usageUnavailable', null, '用量统计暂不可用');
- return;
- }
- const exact = value => dashboardUsageCount(value).toLocaleString(window.__locale || 'zh-CN');
- const label = key => dt('dashboard.' + key, null, key);
- const metrics = document.createElement('div');
- metrics.className = 'token-usage-metrics';
- dashboardUsageMetrics(res.summary).forEach(([key, value]) => {
- const card = document.createElement('div');
- const title = document.createElement('span');
- title.textContent = label(key);
- const count = document.createElement('strong');
- count.textContent = typeof value === 'string' ? value : exact(value);
- card.append(title, count);
- metrics.append(card);
- });
- host.append(metrics);
- if (!dashboardUsageCount(res.summary.events)) {
- const empty = document.createElement('p');
- empty.textContent = dt('dashboard.noTokenUsageYet', null, '暂无用量');
- host.append(empty);
- return;
- }
- // Tables use text nodes: provider model names and conversation IDs are untrusted.
- const table = (titleKey, headings, rows) => {
- const section = document.createElement('section');
- const title = document.createElement('h4');
- title.textContent = label(titleKey);
- const wrap = document.createElement('div');
- wrap.className = 'token-usage-table-wrap';
- const grid = document.createElement('table');
- const caption = document.createElement('caption');
- caption.className = 'sr-only';
- caption.textContent = title.textContent;
- const head = document.createElement('thead');
- const hr = document.createElement('tr');
- headings.forEach(key => {
- const th = document.createElement('th');
- th.scope = 'col';
- th.textContent = label(key);
- hr.append(th);
- });
- head.append(hr);
- const body = document.createElement('tbody');
- rows.forEach(values => {
- const tr = document.createElement('tr');
- values.forEach(value => {
- const td = document.createElement('td');
- td.textContent = String(value == null ? '' : value);
- tr.append(td);
- });
- body.append(tr);
- });
- grid.append(caption, head, body);
- wrap.append(grid);
- section.append(title, wrap);
- host.append(section);
- };
- const counts = row => [exact(row.promptTokens), exact(row.completionTokens), exact(row.cachedTokens),
- exact(row.cacheWriteTokens), exact(row.reasoningTokens), exact(row.totalTokens), exact(row.modelCalls)];
- const fields = ['usageInput', 'usageOutput', 'usageCacheRead', 'usageCacheWrite', 'usageReasoning', 'usageTotal', 'usageCalls'];
- table('usageByModel', ['usageModel', 'usageShare', ...fields], (res.byModel || []).map(row => [row.label || row.key,
- dashboardUsageCount(res.summary.totalTokens) > 0 ? (dashboardUsageCount(row.totalTokens) / dashboardUsageCount(res.summary.totalTokens) * 100).toFixed(1) + '%' : '—', ...counts(row)]));
- const trendTitle = document.createElement('h4');
- trendTitle.textContent = label('usageTrend');
- const trend = document.createElement('div');
- trend.className = 'token-usage-trend';
- const days = (res.byDay || []).slice().reverse();
- const peak = Math.max(1, ...days.map(row => dashboardUsageCount(row.totalTokens)));
- days.forEach(row => {
- const bar = document.createElement('div');
- bar.className = 'token-usage-day';
- const count = document.createElement('span');
- count.textContent = formatTokenUsageCompact(row.totalTokens);
- const fill = document.createElement('div');
- fill.className = 'token-usage-day-bar';
- fill.style.height = Math.max(1, dashboardUsageCount(row.totalTokens) / peak * 90) + 'px';
- const date = document.createElement('span');
- date.textContent = String(row.key || '').slice(5);
- bar.title = row.key + ': ' + exact(row.totalTokens);
- bar.append(count, fill, date);
- trend.append(bar);
- });
- host.append(trendTitle, trend);
- table('usageByDay', ['usageDate', ...fields], (res.byDay || []).map(row => [row.key, ...counts(row)]));
- table('usageRecent', ['usageTime', 'usageModel', 'usageStatus', 'usageTotal', 'usageCalls'], (res.recent || []).map(row => {
- const time = new Date(row.createdAt);
- return [Number.isFinite(time.getTime()) ? time.toLocaleString(window.__locale || 'zh-CN') : '—',
- row.model || '—', row.reason === 'final' ? label('usageFinal') : row.reason === 'partial' ? label('usagePartial') : (row.reason || '—'), exact(row.totalTokens), exact(row.modelCalls)];
- }));
-}
diff --git a/web/static/js/router.js b/web/static/js/router.js
index ddb3955d..b98c613c 100644
--- a/web/static/js/router.js
+++ b/web/static/js/router.js
@@ -1,9 +1,9 @@
// 页面路由管理
let currentPage = null;
-/** chat、漏洞管理页在切换时保留当前 hash 上的查询串(如 ?conversation= / ?conversation_id=) */
+/** 对话、漏洞管理和设置页切换时保留查询串(会话 ID 或设置分区)。 */
function buildHashForPage(pageId) {
- if (pageId !== 'chat' && pageId !== 'vulnerabilities') {
+ if (pageId !== 'chat' && pageId !== 'vulnerabilities' && pageId !== 'settings') {
return pageId;
}
const full = window.location.hash.slice(1);
@@ -111,7 +111,7 @@ function initRouter() {
let pageId = hashParts[0].replace(/^#?\//, '');
if (pageId === 'c2') pageId = 'c2-listeners';
// 一键更新已并进系统设置页的分区菜单:#system-update 这条老深链落到设置页的那一区。
- const settingsSection = pageId === 'system-update' ? 'update' : '';
+ const settingsSection = pageId === 'system-update' ? 'update' : pageId === 'settings' && new URLSearchParams(hashParts.slice(1).join('?')).get('section') === 'token-usage' ? 'token-usage' : '';
if (settingsSection) pageId = 'settings';
if (pageId && ['dashboard', 'chat', 'hitl', 'tool-guard', 'asset-overview', 'asset-library', 'info-collect', 'projects', 'vulnerabilities', 'webshell', 'chat-files', 'mcp-monitor', 'mcp-management', 'knowledge-management', 'knowledge-retrieval-logs', 'roles-management', 'platform-rbac', 'workflows', 'skills-monitor', 'skills-management', 'agents-management', 'settings', 'tasks', 'c2-listeners', 'c2-sessions', 'c2-tasks', 'c2-payloads', 'c2-events', 'c2-profiles'].includes(pageId)) {
switchPage(pageId);
@@ -541,6 +541,12 @@ async function initPage(pageId) {
if (updateSection && updateSection.classList.contains('active') && typeof loadUpdateConsole === 'function') {
loadUpdateConsole();
}
+ // Returning through the regular settings nav reloads a retained usage panel.
+ // Deep links are loaded by switchSettingsSection after switchPage returns.
+ const tokenSection = document.getElementById('settings-section-token-usage');
+ if (tokenSection && tokenSection.classList.contains('active') && window.location.hash !== '#settings?section=token-usage' && typeof refreshTokenUsage === 'function') {
+ refreshTokenUsage();
+ }
break;
case 'roles-management':
// 初始化角色管理页面
@@ -622,6 +628,9 @@ async function initPage(pageId) {
if (pageId !== 'settings' && typeof stopUpdatePolling === 'function') {
stopUpdatePolling();
}
+ if (pageId !== 'settings' && typeof stopTokenUsageRequests === 'function') {
+ stopTokenUsageRequests();
+ }
}
// 页面加载完成后初始化路由
@@ -639,7 +648,7 @@ document.addEventListener('DOMContentLoaded', function() {
if (pageId === 'c2') pageId = 'c2-listeners';
// 与首屏解析同一套别名:#system-update 落到系统设置页的「一键更新」分区。
- const settingsSection = pageId === 'system-update' ? 'update' : '';
+ const settingsSection = pageId === 'system-update' ? 'update' : pageId === 'settings' && new URLSearchParams(hashParts.slice(1).join('?')).get('section') === 'token-usage' ? 'token-usage' : '';
if (settingsSection) pageId = 'settings';
if (pageId && ['dashboard', 'chat', 'hitl', 'tool-guard', 'asset-overview', 'asset-library', 'info-collect', 'projects', 'tasks', 'workflows', 'vulnerabilities', 'webshell', 'chat-files', 'mcp-monitor', 'mcp-management', 'knowledge-management', 'knowledge-retrieval-logs', 'roles-management', 'platform-rbac', 'skills-monitor', 'skills-management', 'agents-management', 'settings', 'c2-listeners', 'c2-sessions', 'c2-tasks', 'c2-payloads', 'c2-events', 'c2-profiles'].includes(pageId)) {
switchPage(pageId);
diff --git a/web/static/js/settings.js b/web/static/js/settings.js
index 9e371efd..0eb2eab9 100644
--- a/web/static/js/settings.js
+++ b/web/static/js/settings.js
@@ -661,6 +661,13 @@ function switchSettingsSection(section) {
return;
}
+ // Unknown hash sections must not hide every settings panel.
+ const requestedContent = document.getElementById(`settings-section-${section}`);
+ if (!requestedContent) return;
+ if (window.location.hash.split('?')[0] === '#settings') {
+ history.replaceState(null, '', section === 'token-usage' ? '#settings?section=token-usage' : '#settings');
+ }
+
// 更新导航项状态
document.querySelectorAll('.settings-nav-item').forEach(item => {
item.classList.remove('active');
@@ -678,6 +685,11 @@ function switchSettingsSection(section) {
if (activeContent) {
activeContent.classList.add('active');
initSettingsCustomSelects(activeContent);
+ }
+ if (section === 'token-usage' && typeof refreshTokenUsage === 'function') {
+ refreshTokenUsage();
+ } else if (typeof stopTokenUsageRequests === 'function') {
+ stopTokenUsageRequests();
}
if (section === 'robots' && typeof window.loadVulnerabilityAlertSubscription === 'function') {
window.loadVulnerabilityAlertSubscription();
diff --git a/web/static/js/token-usage-analysis.test.cjs b/web/static/js/token-usage-analysis.test.cjs
index a6c61896..de24409d 100644
--- a/web/static/js/token-usage-analysis.test.cjs
+++ b/web/static/js/token-usage-analysis.test.cjs
@@ -2,41 +2,79 @@ const fs = require('node:fs');
const vm = require('node:vm');
const test = require('node:test');
const assert = require('node:assert/strict');
-const source = fs.readFileSync('web/static/js/dashboard.js', 'utf8');
+const source = fs.readFileSync('web/static/js/token-usage.js', 'utf8');
const harness = () => {
- const context = { document: {}, dashboardState: { tokenDays: 7 }, refreshDashboard() {} };
+ const context = { document: { addEventListener() {} }, window: {}, AbortController };
vm.createContext(context);
- vm.runInContext(source.slice(source.indexOf('function openDashboardTokenUsage()')), context);
+ vm.runInContext(source, context);
return context;
};
test('cache and reasoning details do not inflate total or double-count input', () => {
const ctx = harness();
- const metrics = ctx.dashboardUsageMetrics({ totalTokens: 120, promptTokens: 100, completionTokens: 20, cachedTokens: 40, cacheWriteTokens: 30, reasoningTokens: 10, modelCalls: 1 });
+ const metrics = ctx.tokenUsageMetrics({ totalTokens: 120, promptTokens: 100, completionTokens: 20, cachedTokens: 40, cacheWriteTokens: 30, reasoningTokens: 10, modelCalls: 1 });
const values = Object.fromEntries(metrics);
assert.equal(values.usageTotal, 120);
assert.equal(values.usageCacheWrite, 30);
assert.equal(values.usageCacheRate, '40.0%');
- assert.equal(Object.fromEntries(ctx.dashboardUsageMetrics({})).usageCacheRate, '—');
- assert.equal(ctx.dashboardUsageCount(Infinity), 0);
- assert.equal(ctx.dashboardUsageCount(-12), 0);
+ assert.equal(Object.fromEntries(ctx.tokenUsageMetrics({})).usageCacheRate, '—');
+ assert.equal(ctx.tokenUsageCount(Infinity), 0);
+ assert.equal(ctx.tokenUsageCount(-12), 0);
});
test('period selection refreshes once and rejects arbitrary periods', () => {
const ctx = harness();
let calls = 0;
- ctx.refreshDashboard = () => { calls++; };
+ ctx.refreshTokenUsage = () => { calls++; };
ctx.document.getElementById = () => ({ textContent: '' });
- ctx.changeDashboardTokenPeriod('30');
- ctx.changeDashboardTokenPeriod('999');
- assert.equal(ctx.dashboardState.tokenDays, 30);
+ ctx.changeTokenUsagePeriod('30');
+ ctx.changeTokenUsagePeriod('999');
+ assert.equal(ctx.tokenUsageState.days, 30);
assert.equal(calls, 1);
});
+test('cache hit ratio uses input tokens, clamps invalid detail and handles missing input', () => {
+ const ctx = harness();
+ assert.equal(ctx.tokenUsageCacheRate({ promptTokens: 1000, cachedTokens: 930, totalTokens: 1100 }), '93.0%');
+ assert.equal(ctx.tokenUsageCacheRate({ promptTokens: 1000, cachedTokens: 0 }), '0.0%');
+ assert.equal(ctx.tokenUsageCacheRate({ promptTokens: 10, cachedTokens: 30 }), '100.0%');
+ assert.equal(ctx.tokenUsageCacheRate({ promptTokens: 0, cachedTokens: 30 }), '—');
+ assert.equal(ctx.tokenUsageCacheRate(null), '—');
+});
+
+test('detail requests stay project scoped and discard late results after a period change', async () => {
+ const ctx = harness();
+ const host = { setAttribute() {}, removeAttribute() {}, textContent: '' };
+ ctx.document.getElementById = id => id === 'settings-token-analysis' ? host : null;
+ ctx.getActiveProjectId = () => 'project / sample';
+ const requests = [];
+ ctx.apiFetch = (url, options) => new Promise(resolve => requests.push({ url, options, resolve }));
+ const rendered = [];
+ ctx.renderTokenUsageAnalysis = value => rendered.push(value);
+ const first = ctx.refreshTokenUsage();
+ ctx.tokenUsageState.days = 30;
+ const second = ctx.refreshTokenUsage();
+ assert.ok(requests[0].options.signal.aborted);
+ assert.match(requests[1].url, /days=30.*project_id=project%20%2F%20sample/);
+ requests[1].resolve({ ok: true, json: async () => ({ summary: { totalTokens: 30 } }) });
+ await second;
+ requests[0].resolve({ ok: true, json: async () => ({ summary: { totalTokens: 7 } }) });
+ await first;
+ assert.equal(rendered.length, 1);
+ assert.equal(rendered[0].summary.totalTokens, 30);
+ const pending = ctx.refreshTokenUsage();
+ ctx.stopTokenUsageRequests();
+ requests[2].resolve({ ok: true, json: async () => ({ summary: { totalTokens: 90 } }) });
+ await pending;
+ assert.equal(rendered.length, 1, 'leaving the section must invalidate outstanding results');
+});
+
test('all supported languages expose usage labels and interpolation placeholders', () => {
for (const locale of ['zh-CN', 'en-US', 'ru-RU']) {
const data = JSON.parse(fs.readFileSync(`web/static/i18n/${locale}.json`, 'utf8'));
- for (const key of ['usageView', 'usageScope', 'usageCacheRead', 'usageCacheWrite', 'usageTrend']) assert.ok(data.dashboard[key]);
+ for (const key of ['usageView', 'usageScope', 'usageCacheRead', 'usageCacheWrite', 'usageTrend', 'usageCacheHitRate']) assert.ok(data.dashboard[key]);
+ assert.ok(data.settings.nav.tokenUsage);
+ assert.match(data.dashboard.usageCacheHitRate, /\{\{rate\}\}/);
assert.match(data.dashboard.tokenUsageSub, /\{\{days\}\}/);
assert.match(data.chat.turnTokenUsageTitle, /\{\{cacheWrite\}\}/);
}
diff --git a/web/static/js/token-usage.js b/web/static/js/token-usage.js
new file mode 100644
index 00000000..34a2da73
--- /dev/null
+++ b/web/static/js/token-usage.js
@@ -0,0 +1,197 @@
+// Token detail data belongs to the settings section; the dashboard keeps a
+// separate fixed seven-day summary.
+var tokenUsageState = { days: 7, controller: null, requestSequence: 0, result: null };
+
+function tokenUsageText(key, opts, fallback) {
+ if (typeof window.t === 'function') {
+ const text = window.t(key, opts);
+ if (text && text !== key) return text;
+ }
+ return fallback == null ? key : fallback;
+}
+
+function openDashboardTokenUsage() {
+ if (window.location.hash === '#settings?section=token-usage') {
+ switchPage('settings');
+ switchSettingsSection('token-usage');
+ } else {
+ window.location.hash = 'settings?section=token-usage';
+ }
+}
+
+function stopTokenUsageRequests() {
+ tokenUsageState.requestSequence++;
+ if (tokenUsageState.controller) tokenUsageState.controller.abort();
+ tokenUsageState.controller = null;
+}
+
+async function refreshTokenUsage() {
+ const host = document.getElementById('settings-token-analysis');
+ if (!host) return;
+ stopTokenUsageRequests();
+ const sequence = tokenUsageState.requestSequence;
+ const controller = new AbortController();
+ tokenUsageState.controller = controller;
+ host.setAttribute('aria-busy', 'true');
+ host.textContent = tokenUsageText('common.loading', null, '加载中…');
+ const select = document.getElementById('settings-token-days');
+ if (select) select.value = String(tokenUsageState.days);
+ let url = '/api/usage/tokens?days=' + tokenUsageState.days + '&limit=20';
+ const projectId = typeof getActiveProjectId === 'function' ? getActiveProjectId() : '';
+ if (projectId) url += '&project_id=' + encodeURIComponent(projectId);
+ try {
+ const response = await apiFetch(url, { signal: controller.signal });
+ const result = response && response.ok ? await response.json() : null;
+ if (sequence !== tokenUsageState.requestSequence) return;
+ tokenUsageState.result = result;
+ renderTokenUsageAnalysis(result);
+ } catch (_) {
+ if (sequence !== tokenUsageState.requestSequence) return;
+ tokenUsageState.result = null;
+ renderTokenUsageAnalysis(null);
+ } finally {
+ if (sequence === tokenUsageState.requestSequence) {
+ tokenUsageState.controller = null;
+ host.removeAttribute('aria-busy');
+ }
+ }
+}
+
+function changeTokenUsagePeriod(value) {
+ const days = Number(value);
+ if (![7, 30, 90].includes(days)) return;
+ tokenUsageState.days = days;
+ refreshTokenUsage();
+}
+
+function tokenUsageCacheRate(summary) {
+ const input = tokenUsageCount(summary && summary.promptTokens);
+ const cached = tokenUsageCount(summary && summary.cachedTokens);
+ return input > 0 ? (Math.min(cached, input) / input * 100).toFixed(1) + '%' : '—';
+}
+
+function tokenUsageCount(value) {
+ const n = Number(value);
+ return Number.isFinite(n) && n > 0 ? Math.trunc(n) : 0;
+}
+
+function tokenUsageMetrics(summary) {
+ const input = tokenUsageCount(summary.promptTokens);
+ const cached = tokenUsageCount(summary.cachedTokens);
+ return [
+ ['usageTotal', summary.totalTokens],
+ ['usageInput', input],
+ ['usageOutput', summary.completionTokens],
+ ['usageCacheRead', cached],
+ ['usageCacheWrite', summary.cacheWriteTokens],
+ ['usageReasoning', summary.reasoningTokens],
+ ['usageCalls', summary.modelCalls],
+ ['usageCacheRate', tokenUsageCacheRate(summary)]
+ ];
+}
+
+document.addEventListener('languagechange', function () {
+ if (tokenUsageState.controller) return;
+ const page = document.getElementById('page-settings');
+ const section = document.getElementById('settings-section-token-usage');
+ if (page && page.classList.contains('active') && section && section.classList.contains('active')) {
+ renderTokenUsageAnalysis(tokenUsageState.result);
+ }
+});
+
+function renderTokenUsageAnalysis(res) {
+ const host = document.getElementById('settings-token-analysis');
+ if (!host) return;
+ host.replaceChildren();
+ if (!res || !res.summary) {
+ host.textContent = tokenUsageText('dashboard.usageUnavailable', null, '用量统计暂不可用');
+ return;
+ }
+ const exact = value => tokenUsageCount(value).toLocaleString(window.__locale || 'zh-CN');
+ const label = key => tokenUsageText('dashboard.' + key, null, key);
+ const metrics = document.createElement('div');
+ metrics.className = 'token-usage-metrics';
+ tokenUsageMetrics(res.summary).forEach(([key, value]) => {
+ const card = document.createElement('div');
+ const title = document.createElement('span');
+ title.textContent = label(key);
+ const count = document.createElement('strong');
+ count.textContent = typeof value === 'string' ? value : exact(value);
+ card.append(title, count);
+ metrics.append(card);
+ });
+ host.append(metrics);
+ if (!tokenUsageCount(res.summary.events)) {
+ const empty = document.createElement('p');
+ empty.textContent = tokenUsageText('dashboard.noTokenUsageYet', null, '暂无用量');
+ host.append(empty);
+ return;
+ }
+ // Tables use text nodes: provider model names and conversation IDs are untrusted.
+ const table = (titleKey, headings, rows) => {
+ const section = document.createElement('section');
+ const title = document.createElement('h4');
+ title.textContent = label(titleKey);
+ const wrap = document.createElement('div');
+ wrap.className = 'token-usage-table-wrap';
+ const grid = document.createElement('table');
+ const caption = document.createElement('caption');
+ caption.className = 'sr-only';
+ caption.textContent = title.textContent;
+ const head = document.createElement('thead');
+ const hr = document.createElement('tr');
+ headings.forEach(key => {
+ const th = document.createElement('th');
+ th.scope = 'col';
+ th.textContent = label(key);
+ hr.append(th);
+ });
+ head.append(hr);
+ const body = document.createElement('tbody');
+ rows.forEach(values => {
+ const tr = document.createElement('tr');
+ values.forEach(value => {
+ const td = document.createElement('td');
+ td.textContent = String(value == null ? '' : value);
+ tr.append(td);
+ });
+ body.append(tr);
+ });
+ grid.append(caption, head, body);
+ wrap.append(grid);
+ section.append(title, wrap);
+ host.append(section);
+ };
+ const counts = row => [exact(row.promptTokens), exact(row.completionTokens), exact(row.cachedTokens),
+ exact(row.cacheWriteTokens), exact(row.reasoningTokens), exact(row.totalTokens), exact(row.modelCalls)];
+ const fields = ['usageInput', 'usageOutput', 'usageCacheRead', 'usageCacheWrite', 'usageReasoning', 'usageTotal', 'usageCalls'];
+ table('usageByModel', ['usageModel', 'usageShare', ...fields], (res.byModel || []).map(row => [row.label || row.key,
+ tokenUsageCount(res.summary.totalTokens) > 0 ? (tokenUsageCount(row.totalTokens) / tokenUsageCount(res.summary.totalTokens) * 100).toFixed(1) + '%' : '—', ...counts(row)]));
+ const trendTitle = document.createElement('h4');
+ trendTitle.textContent = label('usageTrend');
+ const trend = document.createElement('div');
+ trend.className = 'token-usage-trend';
+ const days = (res.byDay || []).slice().reverse();
+ const peak = Math.max(1, ...days.map(row => tokenUsageCount(row.totalTokens)));
+ days.forEach(row => {
+ const bar = document.createElement('div');
+ bar.className = 'token-usage-day';
+ const count = document.createElement('span');
+ count.textContent = formatTokenUsageCompact(row.totalTokens);
+ const fill = document.createElement('div');
+ fill.className = 'token-usage-day-bar';
+ fill.style.height = Math.max(1, tokenUsageCount(row.totalTokens) / peak * 90) + 'px';
+ const date = document.createElement('span');
+ date.textContent = String(row.key || '').slice(5);
+ bar.title = row.key + ': ' + exact(row.totalTokens);
+ bar.append(count, fill, date);
+ trend.append(bar);
+ });
+ host.append(trendTitle, trend);
+ table('usageByDay', ['usageDate', ...fields], (res.byDay || []).map(row => [row.key, ...counts(row)]));
+ table('usageRecent', ['usageTime', 'usageModel', 'usageStatus', 'usageTotal', 'usageCalls'], (res.recent || []).map(row => {
+ const time = new Date(row.createdAt);
+ return [Number.isFinite(time.getTime()) ? time.toLocaleString(window.__locale || 'zh-CN') : '—',
+ row.model || '—', row.reason === 'final' ? label('usageFinal') : row.reason === 'partial' ? label('usagePartial') : (row.reason || '—'), exact(row.totalTokens), exact(row.modelCalls)];
+ }));
+}
diff --git a/web/static/js/update-ui.test.cjs b/web/static/js/update-ui.test.cjs
index a3bf65b4..1e42d24b 100644
--- a/web/static/js/update-ui.test.cjs
+++ b/web/static/js/update-ui.test.cjs
@@ -435,7 +435,7 @@ test('the console lives inside the settings page as its own section', () => {
// Both hash entry points carry the alias, and the retired page id is gone from the whitelists:
// #system-update has to land on 系统设置 with its update section selected.
- const aliases = [...router.matchAll(/const settingsSection = pageId === 'system-update' \? 'update' : '';/g)];
+ const aliases = [...router.matchAll(/const settingsSection = pageId === 'system-update' \? 'update' : /g)];
assert.equal(aliases.length, 2, 'both hash parsers must normalize #system-update into the settings section');
const selects = [...router.matchAll(/if \(settingsSection && typeof switchSettingsSection === 'function'\) \{[\s\S]{0,80}?switchSettingsSection\(settingsSection\);/g)];
assert.equal(selects.length, 2, 'both hash paths must open the update section after switching the page');
diff --git a/web/templates/index.html b/web/templates/index.html
index 3ced8a4a..ad0c85d9 100644
--- a/web/templates/index.html
+++ b/web/templates/index.html
@@ -39,14 +39,14 @@
}
})();
-
+
-
+
-
-
-
- 查看用量详情
-
-
-
-
- 统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。模型按运行配置归类,切换模型的运行可能混合用量。
-
-
@@ -3615,6 +3603,9 @@
基本设置
+
+ Token 用量
+
人机协同
@@ -3650,6 +3641,23 @@
+
+
+
+
+
+
+
统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。模型按运行配置归类,切换模型的运行可能混合用量。
+
+
+
@@ -7017,7 +7016,7 @@
-
+
From 4badef67c12cc91b3285a72401e54aadafd8eef8 Mon Sep 17 00:00:00 2001
From: Sycun <165354365+Sycun@users.noreply.github.com>
Date: Mon, 12 Oct 2026 00:00:26 +0800
Subject: [PATCH 4/5] style: show only cache hit rate below dashboard token
total
---
docs/zh-CN/token-usage-monitoring.md | 2 +-
web/static/i18n/en-US.json | 2 +-
web/static/i18n/ru-RU.json | 2 +-
web/static/i18n/zh-CN.json | 2 +-
web/static/js/dashboard.js | 4 +---
web/static/js/token-usage-analysis.test.cjs | 1 -
web/templates/index.html | 2 +-
7 files changed, 6 insertions(+), 9 deletions(-)
diff --git a/docs/zh-CN/token-usage-monitoring.md b/docs/zh-CN/token-usage-monitoring.md
index 555bd7b8..80458a69 100644
--- a/docs/zh-CN/token-usage-monitoring.md
+++ b/docs/zh-CN/token-usage-monitoring.md
@@ -29,7 +29,7 @@ DeepSeek 的未命中输入不等于 Claude 的缓存写入。不能根据文本
## 功能入口与数据流
-点击首页「Token 用量」卡片进入「系统设置 → Token 用量」,也可直接从设置二级菜单打开。首页卡片显示近 7 天总用量,副标仅用一行显示今日用量与缓存命中率(缓存读取 Token / 输入 Token),调用次数保留在详情页。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。详情页独立加载,支持手动刷新与请求取消,切换周期不会刷新整个仪表盘;刷新页面可保持该设置分区。
+点击首页「Token 用量」卡片进入「系统设置 → Token 用量」,也可直接从设置二级菜单打开。首页卡片显示近 7 天总用量,副标仅显示缓存命中率(缓存读取 Token / 输入 Token),调用次数和每日用量保留在详情页。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。详情页独立加载,支持手动刷新与请求取消,切换周期不会刷新整个仪表盘;刷新页面可保持该设置分区。
运行事件 → 流式/非流式用量累加 → `eino_usage_summary` → `process_details` 与 `model_token_usage` → 现有 `/api/usage/tokens`、对话用量接口 → 首页与聊天摘要。
diff --git a/web/static/i18n/en-US.json b/web/static/i18n/en-US.json
index 4a3ad926..932ccf16 100644
--- a/web/static/i18n/en-US.json
+++ b/web/static/i18n/en-US.json
@@ -288,7 +288,7 @@
"successRate": "Tool success rate",
"tokenUsage": "Token usage",
"usageCacheHitRate": "Cache hit {{rate}}",
- "tokenUsageSub": "Today {{today}} · Cache hit {{rate}}",
+ "tokenUsageSub": "Cache hit {{rate}}",
"noTokenUsageYet": "No usage yet",
"clickToViewTasks": "Click to view tasks",
"clickToViewChat": "Click to view conversations",
diff --git a/web/static/i18n/ru-RU.json b/web/static/i18n/ru-RU.json
index d060b292..9e833896 100644
--- a/web/static/i18n/ru-RU.json
+++ b/web/static/i18n/ru-RU.json
@@ -288,7 +288,7 @@
"successRate": "Успешность инструментов",
"tokenUsage": "Расход токенов",
"usageCacheHitRate": "Попадания в кэш {{rate}}",
- "tokenUsageSub": "Сегодня {{today}} · Кэш {{rate}}",
+ "tokenUsageSub": "Кэш {{rate}}",
"noTokenUsageYet": "Расхода пока нет",
"clickToViewTasks": "Открыть задачи",
"clickToViewChat": "Открыть диалоги",
diff --git a/web/static/i18n/zh-CN.json b/web/static/i18n/zh-CN.json
index 77ed40c6..e53ee222 100644
--- a/web/static/i18n/zh-CN.json
+++ b/web/static/i18n/zh-CN.json
@@ -288,7 +288,7 @@
"successRate": "工具执行成功率",
"tokenUsage": "Token 用量",
"usageCacheHitRate": "缓存命中 {{rate}}",
- "tokenUsageSub": "今日 {{today}} · 缓存命中 {{rate}}",
+ "tokenUsageSub": "缓存命中 {{rate}}",
"noTokenUsageYet": "暂无用量",
"clickToViewTasks": "点击查看任务管理",
"clickToViewChat": "点击查看对话",
diff --git a/web/static/js/dashboard.js b/web/static/js/dashboard.js
index 5ad07c76..50f8d207 100644
--- a/web/static/js/dashboard.js
+++ b/web/static/js/dashboard.js
@@ -717,7 +717,6 @@ function renderDashboardTokenUsage(res) {
}
const cacheRate = tokenUsageCacheRate(summary);
const total = Number(summary.totalTokens || 0);
- const today = res && res.today ? Number(res.today.totalTokens || 0) : 0;
if (!Number.isFinite(total) || total <= 0) {
setEl('dashboard-kpi-token-usage', '0');
setKpiSubText('dashboard-kpi-token-sub-text', dt('dashboard.noTokenUsageYet', null, '暂无用量'));
@@ -726,9 +725,8 @@ function renderDashboardTokenUsage(res) {
setEl('dashboard-kpi-token-usage', formatTokenUsageCompact(total));
setKpiSubText('dashboard-kpi-token-sub-text',
dt('dashboard.tokenUsageSub', {
- today: formatTokenUsageCompact(today),
rate: cacheRate
- }, '今日 ' + formatTokenUsageCompact(today) + ' · 缓存命中 ' + cacheRate));
+ }, '缓存命中 ' + cacheRate));
}
function formatTokenUsageCompact(num) {
diff --git a/web/static/js/token-usage-analysis.test.cjs b/web/static/js/token-usage-analysis.test.cjs
index 9a39a482..86b98ddb 100644
--- a/web/static/js/token-usage-analysis.test.cjs
+++ b/web/static/js/token-usage-analysis.test.cjs
@@ -75,7 +75,6 @@ test('all supported languages expose usage labels and interpolation placeholders
for (const key of ['usageView', 'usageScope', 'usageCacheRead', 'usageCacheWrite', 'usageTrend', 'usageCacheHitRate']) assert.ok(data.dashboard[key]);
assert.ok(data.settings.nav.tokenUsage);
assert.match(data.dashboard.usageCacheHitRate, /\{\{rate\}\}/);
- assert.match(data.dashboard.tokenUsageSub, /\{\{today\}\}/);
assert.match(data.dashboard.tokenUsageSub, /\{\{rate\}\}/);
assert.match(data.chat.turnTokenUsageTitle, /\{\{cacheWrite\}\}/);
}
diff --git a/web/templates/index.html b/web/templates/index.html
index 949bc0f6..147d3cee 100644
--- a/web/templates/index.html
+++ b/web/templates/index.html
@@ -7016,7 +7016,7 @@
-
+
From 56d29b7054dc2f6ff36cedc91723ce3ce458a438 Mon Sep 17 00:00:00 2001
From: Sycun <165354365+Sycun@users.noreply.github.com>
Date: Mon, 12 Oct 2026 00:10:37 +0800
Subject: [PATCH 5/5] feat: refine token analytics with interactive trends and
cache breakdown
---
docs/zh-CN/token-usage-monitoring.md | 14 ++
web/static/css/style.css | 92 ++++++--
web/static/i18n/en-US.json | 13 ++
web/static/i18n/ru-RU.json | 13 ++
web/static/i18n/zh-CN.json | 13 ++
web/static/js/token-usage-analysis.test.cjs | 12 +
web/static/js/token-usage.js | 238 ++++++++++++++------
web/templates/index.html | 11 +-
8 files changed, 310 insertions(+), 96 deletions(-)
diff --git a/docs/zh-CN/token-usage-monitoring.md b/docs/zh-CN/token-usage-monitoring.md
index 80458a69..9a60fd48 100644
--- a/docs/zh-CN/token-usage-monitoring.md
+++ b/docs/zh-CN/token-usage-monitoring.md
@@ -31,6 +31,20 @@ DeepSeek 的未命中输入不等于 Claude 的缓存写入。不能根据文本
点击首页「Token 用量」卡片进入「系统设置 → Token 用量」,也可直接从设置二级菜单打开。首页卡片显示近 7 天总用量,副标仅显示缓存命中率(缓存读取 Token / 输入 Token),调用次数和每日用量保留在详情页。支持当前项目范围、7/30/90 天切换、八项指标、最多 20 项运行模型排行、每日趋势与完整日明细、最多 20 项最近运行。详情页独立加载,支持手动刷新与请求取消,切换周期不会刷新整个仪表盘;刷新页面可保持该设置分区。
+详情页采用四项核心指标(总量、输入、输出、缓存读取占输入)与四项次级指标(调用、缓存读取、缓存写入、推理)的层级布局。趋势可切换总 Token、模型调用与缓存命中率,鼠标悬停或键盘聚焦柱形可查看日期与精确数字;切换图表指标不再请求 API。缓存环形图拆分缓存读取与其余输入,不把缓存或推理再次叠加到总量。模型明细展示占比条,每日数字明细默认折叠,最近运行区分完整与部分记录。统计口径可展开查看。
+
+每日图表沿用 API 返回的服务端日期,只补齐已返回日期之间无记录的空档,不根据浏览器时区猜测查询终点。小屏图表和宽表在自己的区域内横向滚动。没有记录和无法获取统计分别展示空状态与不可用状态。
+
+### UI 调研依据(2026-10-12)
+
+| 参考 | 采用的设计 |
+| --- | --- |
+| [DeepSeek Context Caching](https://api-docs.deepseek.com/guides/kv_cache/) | 使用其明确的缓存命中/未命中输入定义,设计缓存构成视图;比例按 Token 而非请求次数计算 |
+| [LiteLLM Usage](https://docs.litellm.ai/docs/proxy/ui/chat_ui) | 周期选择、核心统计与使用日志分层;本项目保留已有数据范围,不新增无法准确计量的费用或成功率 |
+| [Langfuse Custom Dashboards](https://langfuse.com/docs/metrics/features/custom-dashboards) | 将汇总、时间趋势、模型分布拆为独立可读区域,并让趋势指标可切换 |
+
+DeepSeek 和 GLM 控制台的完整页面本轮未能公开读取,因此本轮视觉设计以能核实的开源面板为依据。没有声称复刻它们当前登录后的界面。项目也没有新增供应商账单、预算或节省金额推算。
+
运行事件 → 流式/非流式用量累加 → `eino_usage_summary` → `process_details` 与 `model_token_usage` → 现有 `/api/usage/tokens`、对话用量接口 → 首页与聊天摘要。
新增 `model_token_usage.cache_write_tokens INTEGER NOT NULL DEFAULT 0`。启动时现有声明式 SQLite schema reconciliation 自动补列;旧数据库无需手工执行迁移。现有事件 ID 幂等写入、外键删除关联和历史回填继续生效。日分组按服务本地时区显示,与首页「今日」边界一致。
diff --git a/web/static/css/style.css b/web/static/css/style.css
index 3258149f..a316b5d1 100644
--- a/web/static/css/style.css
+++ b/web/static/css/style.css
@@ -47220,25 +47220,79 @@ html[data-theme="dark"] { --tool-blocked-color: #f4bc62; }
align-self: flex-start;
}
-/* Provider-reported token analysis, scoped by the dashboard project selector. */
-.token-usage-panel { margin-bottom: 20px; padding: 18px 22px; }
-.token-usage-header { display: flex; align-items: center; justify-content: space-between; gap: 12px; }
-.token-usage-toolbar { display: flex; align-items: center; gap: 12px; margin-top: 18px; }
-.token-usage-toolbar label { white-space: nowrap; }
-.token-usage-toolbar select { padding: 6px 10px; border: 1px solid var(--border-color, #dce2ea); border-radius: 6px; background: var(--bg-secondary, #fff); color: inherit; }
-.token-usage-note { opacity: .72; font-size: 12px; line-height: 1.7; margin: 14px 0; }
-.token-usage-metrics { display: grid; grid-template-columns: repeat(4, minmax(0, 1fr)); gap: 10px; }
-.token-usage-metrics > div { padding: 12px; border: 1px solid var(--border-color, #dce2ea); border-radius: 8px; min-width: 0; }
-.token-usage-metrics span { display: block; font-size: 12px; opacity: .7; }
-.token-usage-metrics strong { display: block; margin-top: 6px; font-size: 20px; overflow-wrap: anywhere; font-variant-numeric: tabular-nums; }
+/* Provider-reported token analytics in System Settings. */
+.token-usage-panel { --token-cache-color: #0d9488; max-width: 1200px; margin: 0 auto 24px; }
+html[data-theme="dark"] .token-usage-panel { --token-cache-color: #2dd4bf; }
+.token-usage-header { display: flex; align-items: center; justify-content: space-between; gap: 16px; margin-bottom: 20px; }
+.token-usage-subtitle { font-size: 13px; color: var(--text-secondary); margin: 8px 0 0; }
+.token-usage-toolbar { display: flex; align-items: center; flex-wrap: wrap; gap: 12px; }
+.token-usage-scope { font-size: 11px; padding: 4px 8px; border-radius: 6px; color: var(--text-secondary); background: var(--bg-secondary); }
+.token-usage-toolbar label { white-space: nowrap; font-size: 13px; }
+.token-usage-toolbar select { padding: 7px 12px; border: 1px solid var(--border-color); border-radius: 8px; background: var(--bg-primary); color: var(--text-primary); }
+.token-usage-note { color: var(--text-secondary); font-size: 12px; line-height: 1.7; margin: 16px 0 20px; }
+.token-usage-note summary { cursor: pointer; width: fit-content; }
+.token-usage-note p { margin: 8px 0 0; max-width: 960px; }
+.token-usage-metrics { display: grid; grid-template-columns: repeat(4, minmax(0, 1fr)); gap: 12px; }
+.token-usage-metric { min-width: 0; padding: 16px; border: 1px solid var(--border-color); border-radius: 12px; }
+.token-usage-metric span { display: block; color: var(--text-secondary); font-size: 12px; }
+.token-usage-metric strong { display: block; margin-top: 10px; font-size: clamp(20px, 1.65vw, 28px); font-variant-numeric: tabular-nums; overflow-wrap: anywhere; letter-spacing: -.025em; }
+.token-usage-primary [data-metric="usageTotal"] { background: rgba(0, 102, 255, .05); border-color: rgba(0, 102, 255, .18); }
+.token-usage-primary [data-metric="usageTotal"] strong { color: var(--accent-color); }
+.token-usage-primary [data-metric="usageCacheRate"] strong { color: var(--token-cache-color); }
+.token-usage-secondary { margin: 12px 0 24px; gap: 0; padding: 14px 0; border: 1px solid var(--border-color); border-radius: 12px; }
+.token-usage-secondary .token-usage-metric { border: 0; border-radius: 0; padding: 0 16px; }
+.token-usage-secondary .token-usage-metric + .token-usage-metric { border-left: 1px solid var(--border-color); }
+.token-usage-secondary strong { margin-top: 6px; font-size: 18px; }
+.token-usage-charts { display: grid; grid-template-columns: minmax(0, 2fr) minmax(235px, 1fr); gap: 16px; margin-bottom: 24px; }
+.token-usage-chart-card, .token-usage-data-card { min-width: 0; border: 1px solid var(--border-color); border-radius: 12px; padding: 18px; }
+.token-usage-panel h4 { margin: 0 0 16px; font-size: 14px; }
+.token-usage-chart-head { display: flex; flex-wrap: wrap; align-items: center; justify-content: space-between; gap: 12px; margin-bottom: 16px; }
+.token-usage-chart-head h4 { margin: 0; }
+.token-usage-chart-tabs { display: flex; flex-wrap: wrap; gap: 4px; }
+.token-usage-chart-tabs button { cursor: pointer; border: 0; border-radius: 6px; padding: 6px 8px; font: inherit; font-size: 11px; color: var(--text-secondary); background: transparent; }
+.token-usage-chart-tabs button[aria-pressed="true"] { color: var(--accent-color); background: rgba(0, 102, 255, .08); }
+.token-usage-chart-tabs button:focus-visible { outline: 2px solid var(--accent-color); outline-offset: 2px; }
+.token-usage-trend-svg { display: block; width: 100%; height: auto; overflow: visible; }
+.token-usage-svg-wrap { overflow-x: auto; }
+.token-usage-chart-grid { stroke: var(--border-color); stroke-dasharray: 3 4; }
+.token-usage-chart-label { fill: var(--text-secondary); font-size: 11px; }
+.token-usage-chart-tooltip { font-size: 11px; color: var(--text-secondary); line-height: 1.6; min-height: 35px; margin: 8px 0 0; }
+.token-usage-chart-bar { fill: var(--accent-color); opacity: .8; }
+.token-usage-chart-bar:hover, .token-usage-chart-bar:focus { opacity: 1; outline: none; stroke: var(--text-primary); stroke-width: 1; }
+.token-usage-cache-ring { --cache-ratio: 0%; position: relative; width: 148px; height: 148px; margin: 8px auto 18px; border-radius: 50%; background: conic-gradient(var(--token-cache-color) var(--cache-ratio), var(--border-color) 0); display: flex; flex-direction: column; align-items: center; justify-content: center; gap: 4px; }
+.token-usage-cache-ring::before { content: ''; position: absolute; inset: 12px; border-radius: 50%; background: var(--bg-primary); }
+.token-usage-cache-ring strong, .token-usage-cache-ring span { position: relative; }
+.token-usage-cache-ring strong { font-size: 28px; font-variant-numeric: tabular-nums; }
+.token-usage-cache-ring span { color: var(--text-secondary); font-size: 12px; }
+.token-usage-cache-legend { display: flex; justify-content: space-between; gap: 10px; font-size: 12px; margin: 10px 0; }
+.token-usage-cache-legend > span::before { content: ''; display: inline-block; width: 7px; height: 7px; border-radius: 2px; background: var(--border-color); margin-right: 7px; }
+.token-usage-cache-legend.is-cached > span::before { background: var(--token-cache-color); }
+.token-usage-cache-legend strong { font-variant-numeric: tabular-nums; }
+.token-usage-chart-note { font-size: 11px; line-height: 1.6; color: var(--text-secondary); margin: 14px 0 0; }
+.token-usage-data-card { margin-bottom: 16px; }
+.token-usage-data-card > summary { cursor: pointer; font-size: 14px; font-weight: 600; }
+.token-usage-data-card[open] > summary { margin-bottom: 16px; }
.token-usage-table-wrap { overflow-x: auto; }
.token-usage-table-wrap table { width: 100%; border-collapse: collapse; font-size: 12px; font-variant-numeric: tabular-nums; }
-.token-usage-table-wrap th, .token-usage-table-wrap td { padding: 10px; text-align: right; border-bottom: 1px solid var(--border-color, #dce2ea); white-space: nowrap; }
+.token-usage-table-wrap th, .token-usage-table-wrap td { padding: 12px 10px; text-align: right; border-bottom: 1px solid var(--border-color); white-space: nowrap; }
+.token-usage-table-wrap th { font-weight: 500; color: var(--text-secondary); background: var(--bg-secondary); }
.token-usage-table-wrap th:first-child, .token-usage-table-wrap td:first-child { text-align: left; }
-.token-usage-table-wrap td:first-child { max-width: 280px; overflow: hidden; text-overflow: ellipsis; }
-@media (max-width: 640px) { .token-usage-metrics { grid-template-columns: repeat(2, minmax(0, 1fr)); } .token-usage-panel { padding: 14px; } }
-.token-usage-trend { display: flex; align-items: flex-end; gap: 8px; overflow-x: auto; padding: 12px 0; }
-.token-usage-day { display: flex; flex-direction: column; align-items: center; justify-content: flex-end; flex: 1 0 38px; height: 128px; gap: 6px; font-size: 11px; }
-.token-usage-day-bar { width: 70%; max-width: 48px; background: var(--accent-color, #3b82f6); border-radius: 4px 4px 0 0; }
-
-.token-usage-panel h4 { margin: 20px 0 8px; }
+.token-usage-table-wrap td:first-child { max-width: 220px; overflow: hidden; text-overflow: ellipsis; }
+.token-usage-table-wrap tbody tr:last-child td { border-bottom: 0; }
+.token-usage-share { display: flex; align-items: center; justify-content: flex-end; gap: 8px; }
+.token-usage-share-track { width: 48px; height: 4px; border-radius: 4px; background: var(--border-color); overflow: hidden; }
+.token-usage-share-track > span { display: block; height: 100%; background: var(--accent-color); }
+.token-usage-status { display: inline-block; padding: 3px 7px; border-radius: 5px; background: var(--bg-secondary); color: var(--text-secondary); }
+.token-usage-status.is-final { background: rgba(13, 148, 136, .1); color: var(--token-cache-color); }
+.token-usage-status.is-partial { background: rgba(217, 119, 6, .1); color: #d97706; }
+.token-usage-empty { text-align: center; padding: 36px 16px; color: var(--text-secondary); font-size: 13px; }
+@media (max-width: 1000px) { .token-usage-charts { grid-template-columns: 1fr; } }
+@media (max-width: 640px) {
+ .token-usage-metrics { grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 10px; }
+ .token-usage-metric { padding: 14px; }
+ .token-usage-secondary { gap: 14px 0; }
+ .token-usage-secondary .token-usage-metric:nth-child(3) { border-left: 0; }
+ .token-usage-chart-card, .token-usage-data-card { padding: 14px; }
+ .token-usage-subtitle { max-width: 220px; line-height: 1.6; }
+ .token-usage-trend-svg { min-width: 480px; }
+}
diff --git a/web/static/i18n/en-US.json b/web/static/i18n/en-US.json
index 932ccf16..e6817386 100644
--- a/web/static/i18n/en-US.json
+++ b/web/static/i18n/en-US.json
@@ -277,6 +277,19 @@
"capabilities": "Capabilities",
"administration": "Administration"
},
+ "tokenUsageUI": {
+ "chartHint": "Hover or focus a bar for exact usage",
+ "scopeProject": "Current project",
+ "scopeAccessible": "Accessible conversations",
+ "subtitle": "Explore model consumption, caching and usage trends",
+ "scopeNote": "Scope and counting rules",
+ "trendMetric": "Trend metric",
+ "noDailyData": "No daily usage records",
+ "cacheComposition": "Input cache breakdown",
+ "cacheHit": "Cache hit rate",
+ "uncachedInput": "Input without cache reads",
+ "cacheNote": "Cache reads are part of input, not added to the total again. Cache writes are listed separately."
+ },
"dashboard": {
"title": "Dashboard",
"refresh": "Refresh",
diff --git a/web/static/i18n/ru-RU.json b/web/static/i18n/ru-RU.json
index 9e833896..23463753 100644
--- a/web/static/i18n/ru-RU.json
+++ b/web/static/i18n/ru-RU.json
@@ -277,6 +277,19 @@
"capabilities": "Возможности",
"administration": "Администрирование"
},
+ "tokenUsageUI": {
+ "chartHint": "Наведите или выберите столбец для точных значений",
+ "scopeProject": "Текущий проект",
+ "scopeAccessible": "Доступные диалоги",
+ "subtitle": "Расход моделей, использование кэша и динамика",
+ "scopeNote": "Область и правила подсчёта",
+ "trendMetric": "Показатель графика",
+ "noDailyData": "Нет ежедневных данных",
+ "cacheComposition": "Кэш входных токенов",
+ "cacheHit": "Доля попаданий в кэш",
+ "uncachedInput": "Вход без чтения кэша",
+ "cacheNote": "Чтение кэша входит во входные токены и не прибавляется к итогу. Запись кэша указана отдельно."
+ },
"dashboard": {
"title": "Обзор",
"refresh": "Обновить",
diff --git a/web/static/i18n/zh-CN.json b/web/static/i18n/zh-CN.json
index e53ee222..b1b6d7f4 100644
--- a/web/static/i18n/zh-CN.json
+++ b/web/static/i18n/zh-CN.json
@@ -277,6 +277,19 @@
"capabilities": "能力中心",
"administration": "平台管理"
},
+ "tokenUsageUI": {
+ "chartHint": "悬停或聚焦柱形查看精确用量",
+ "scopeProject": "当前项目",
+ "scopeAccessible": "可访问会话",
+ "subtitle": "查看模型消耗、缓存利用与使用趋势",
+ "scopeNote": "统计口径与说明",
+ "trendMetric": "趋势指标",
+ "noDailyData": "暂无每日用量记录",
+ "cacheComposition": "输入缓存构成",
+ "cacheHit": "缓存命中率",
+ "uncachedInput": "未命中缓存的输入",
+ "cacheNote": "缓存读取是输入的一部分,不重复计入总量。缓存写入单独列示。"
+ },
"dashboard": {
"title": "仪表盘",
"refresh": "刷新",
diff --git a/web/static/js/token-usage-analysis.test.cjs b/web/static/js/token-usage-analysis.test.cjs
index 86b98ddb..9c7e5f8d 100644
--- a/web/static/js/token-usage-analysis.test.cjs
+++ b/web/static/js/token-usage-analysis.test.cjs
@@ -42,6 +42,17 @@ test('cache hit ratio uses input tokens, clamps invalid detail and handles missi
assert.equal(ctx.tokenUsageCacheRate(null), '—');
});
+test('daily trends retain server day keys and fill only gaps within returned history', () => {
+ const ctx = harness();
+ const rows = ctx.tokenUsageTimeline([{ key: '2026-10-12', totalTokens: 12 }, { key: '2026-10-10', totalTokens: 10 }, { key: 'invalid', totalTokens: 20 }]);
+ assert.deepEqual(Array.from(rows, row => row.key), ['2026-10-10', '2026-10-11', '2026-10-12']);
+ assert.equal(rows[1].totalTokens, 0);
+ assert.equal(rows[1].events, 0);
+ assert.equal(rows[2].totalTokens, 12);
+ assert.equal(ctx.tokenUsageTimeline([]).length, 0);
+ assert.equal(ctx.tokenUsageTimeline([{ key: '2026-10-10', totalTokens: 10 }]).length, 1);
+});
+
test('detail requests stay project scoped and discard late results after a period change', async () => {
const ctx = harness();
const host = { setAttribute() {}, removeAttribute() {}, textContent: '' };
@@ -74,6 +85,7 @@ test('all supported languages expose usage labels and interpolation placeholders
const data = JSON.parse(fs.readFileSync(`web/static/i18n/${locale}.json`, 'utf8'));
for (const key of ['usageView', 'usageScope', 'usageCacheRead', 'usageCacheWrite', 'usageTrend', 'usageCacheHitRate']) assert.ok(data.dashboard[key]);
assert.ok(data.settings.nav.tokenUsage);
+ for (const key of ['subtitle', 'scopeNote', 'trendMetric', 'cacheComposition', 'cacheHit', 'uncachedInput', 'cacheNote', 'scopeProject', 'scopeAccessible', 'noDailyData']) assert.ok(data.tokenUsageUI[key]);
assert.match(data.dashboard.usageCacheHitRate, /\{\{rate\}\}/);
assert.match(data.dashboard.tokenUsageSub, /\{\{rate\}\}/);
assert.match(data.chat.turnTokenUsageTitle, /\{\{cacheWrite\}\}/);
diff --git a/web/static/js/token-usage.js b/web/static/js/token-usage.js
index 34a2da73..ae55fcd9 100644
--- a/web/static/js/token-usage.js
+++ b/web/static/js/token-usage.js
@@ -1,6 +1,6 @@
// Token detail data belongs to the settings section; the dashboard keeps a
// separate fixed seven-day summary.
-var tokenUsageState = { days: 7, controller: null, requestSequence: 0, result: null };
+var tokenUsageState = { days: 7, controller: null, requestSequence: 0, result: null, trendMetric: 'totalTokens' };
function tokenUsageText(key, opts, fallback) {
if (typeof window.t === 'function') {
@@ -38,6 +38,8 @@ async function refreshTokenUsage() {
if (select) select.value = String(tokenUsageState.days);
let url = '/api/usage/tokens?days=' + tokenUsageState.days + '&limit=20';
const projectId = typeof getActiveProjectId === 'function' ? getActiveProjectId() : '';
+ const scope = document.getElementById('settings-token-scope');
+ if (scope) scope.textContent = tokenUsageText('tokenUsageUI.' + (projectId ? 'scopeProject' : 'scopeAccessible'), null, projectId ? '当前项目' : '可访问会话');
if (projectId) url += '&project_id=' + encodeURIComponent(projectId);
try {
const response = await apiFetch(url, { signal: controller.signal });
@@ -99,60 +101,167 @@ document.addEventListener('languagechange', function () {
}
});
+function tokenUsageNode(tag, className, text) {
+ const node = document.createElement(tag);
+ if (className) node.className = className;
+ if (text != null) node.textContent = text;
+ return node;
+}
+
+// Fill only gaps between returned dates. The API's server-local day keys are
+// authoritative; do not invent a browser-timezone endpoint for the period.
+function tokenUsageTimeline(rows) {
+ const dated = (rows || []).filter(row => /^\d{4}-\d{2}-\d{2}$/.test(row.key || '')).sort((a, b) => a.key.localeCompare(b.key));
+ if (!dated.length) return [];
+ const byDay = new Map(dated.map(row => [row.key, row]));
+ const start = Date.parse(dated[0].key + 'T00:00:00Z');
+ const end = Date.parse(dated[dated.length - 1].key + 'T00:00:00Z');
+ if (!Number.isFinite(start) || !Number.isFinite(end)) return dated;
+ const days = [];
+ for (let time = start; time <= end && days.length < 365; time += 86400000) {
+ const key = new Date(time).toISOString().slice(0, 10);
+ days.push(byDay.get(key) || { key, events: 0, totalTokens: 0, modelCalls: 0, promptTokens: 0 });
+ }
+ return days;
+}
+
+function setTokenUsageTrend(metric) {
+ if (!['totalTokens', 'modelCalls', 'cacheRate'].includes(metric)) return;
+ tokenUsageState.trendMetric = metric;
+ renderTokenUsageAnalysis(tokenUsageState.result);
+ const button = document.querySelector('[data-token-trend="' + metric + '"]');
+ if (button) button.focus();
+}
+
function renderTokenUsageAnalysis(res) {
const host = document.getElementById('settings-token-analysis');
if (!host) return;
host.replaceChildren();
- if (!res || !res.summary) {
- host.textContent = tokenUsageText('dashboard.usageUnavailable', null, '用量统计暂不可用');
- return;
- }
- const exact = value => tokenUsageCount(value).toLocaleString(window.__locale || 'zh-CN');
const label = key => tokenUsageText('dashboard.' + key, null, key);
- const metrics = document.createElement('div');
- metrics.className = 'token-usage-metrics';
- tokenUsageMetrics(res.summary).forEach(([key, value]) => {
- const card = document.createElement('div');
- const title = document.createElement('span');
- title.textContent = label(key);
- const count = document.createElement('strong');
- count.textContent = typeof value === 'string' ? value : exact(value);
- card.append(title, count);
- metrics.append(card);
- });
- host.append(metrics);
- if (!tokenUsageCount(res.summary.events)) {
- const empty = document.createElement('p');
- empty.textContent = tokenUsageText('dashboard.noTokenUsageYet', null, '暂无用量');
+ const ui = key => tokenUsageText('tokenUsageUI.' + key, null, key);
+ const exact = value => tokenUsageCount(value).toLocaleString(window.__locale || 'zh-CN');
+ if (!res || !res.summary) {
+ const empty = tokenUsageNode('div', 'token-usage-empty', label('usageUnavailable'));
host.append(empty);
return;
}
- // Tables use text nodes: provider model names and conversation IDs are untrusted.
- const table = (titleKey, headings, rows) => {
- const section = document.createElement('section');
- const title = document.createElement('h4');
- title.textContent = label(titleKey);
- const wrap = document.createElement('div');
- wrap.className = 'token-usage-table-wrap';
- const grid = document.createElement('table');
- const caption = document.createElement('caption');
- caption.className = 'sr-only';
- caption.textContent = title.textContent;
- const head = document.createElement('thead');
- const hr = document.createElement('tr');
- headings.forEach(key => {
- const th = document.createElement('th');
- th.scope = 'col';
- th.textContent = label(key);
- hr.append(th);
- });
+ const summary = res.summary;
+ const metrics = new Map(tokenUsageMetrics(summary));
+ const primary = tokenUsageNode('div', 'token-usage-metrics token-usage-primary');
+ const secondary = tokenUsageNode('div', 'token-usage-metrics token-usage-secondary');
+ const primaryKeys = ['usageTotal', 'usageInput', 'usageOutput', 'usageCacheRate'];
+ [...primaryKeys, 'usageCalls', 'usageCacheRead', 'usageCacheWrite', 'usageReasoning'].forEach(key => {
+ const value = metrics.get(key);
+ const card = tokenUsageNode('div', 'token-usage-metric');
+ card.dataset.metric = key;
+ card.append(tokenUsageNode('span', '', label(key)), tokenUsageNode('strong', '', typeof value === 'string' ? value : exact(value)));
+ (primaryKeys.includes(key) ? primary : secondary).append(card);
+ });
+ host.append(primary, secondary);
+ if (!tokenUsageCount(summary.events)) {
+ host.append(tokenUsageNode('div', 'token-usage-empty', label('noTokenUsageYet')));
+ return;
+ }
+
+ const chartLayout = tokenUsageNode('div', 'token-usage-charts');
+ const chart = tokenUsageNode('section', 'token-usage-chart-card');
+ const chartHead = tokenUsageNode('div', 'token-usage-chart-head');
+ chartHead.append(tokenUsageNode('h4', '', label('usageTrend')));
+ const tabs = tokenUsageNode('div', 'token-usage-chart-tabs');
+ tabs.setAttribute('role', 'group');
+ tabs.setAttribute('aria-label', ui('trendMetric'));
+ for (const [metric, key] of [['totalTokens', 'usageTotal'], ['modelCalls', 'usageCalls'], ['cacheRate', 'usageCacheRate']]) {
+ const button = tokenUsageNode('button', '', label(key));
+ button.type = 'button';
+ button.dataset.tokenTrend = metric;
+ button.setAttribute('aria-pressed', String(tokenUsageState.trendMetric === metric));
+ button.addEventListener('click', () => setTokenUsageTrend(metric));
+ tabs.append(button);
+ }
+ chartHead.append(tabs);
+ chart.append(chartHead);
+ const tooltip = tokenUsageNode('p', 'token-usage-chart-tooltip', ui('chartHint'));
+ tooltip.setAttribute('aria-live', 'polite');
+ const days = tokenUsageTimeline(res.byDay);
+ const metric = tokenUsageState.trendMetric;
+ const valueOf = row => metric === 'cacheRate' ? (tokenUsageCount(row.promptTokens) ? Math.min(tokenUsageCount(row.cachedTokens), tokenUsageCount(row.promptTokens)) / tokenUsageCount(row.promptTokens) * 100 : 0) : tokenUsageCount(row[metric]);
+ const peak = metric === 'cacheRate' ? 100 : Math.max(1, ...days.map(valueOf));
+ const svgNS = 'http://www.w3.org/2000/svg';
+ const svg = document.createElementNS(svgNS, 'svg');
+ svg.setAttribute('viewBox', '0 0 640 230');
+ svg.setAttribute('role', 'group');
+ svg.setAttribute('aria-label', label('usageTrend'));
+ svg.classList.add('token-usage-trend-svg');
+ const element = (tag, attrs, text) => {
+ const node = document.createElementNS(svgNS, tag);
+ Object.entries(attrs).forEach(([key, value]) => node.setAttribute(key, String(value)));
+ if (text != null) node.textContent = text;
+ return node;
+ };
+ for (let tick = 0; tick <= 4; tick++) {
+ const y = 18 + tick * 44;
+ svg.append(element('line', { x1: 54, x2: 624, y1: y, y2: y, class: 'token-usage-chart-grid' }));
+ svg.append(element('text', { x: 46, y: y + 4, 'text-anchor': 'end', class: 'token-usage-chart-label' }, metric === 'cacheRate' ? (100 - tick * 25) + '%' : formatTokenUsageCompact(peak * (4 - tick) / 4)));
+ }
+ const slot = 570 / Math.max(days.length, 1);
+ const every = Math.max(1, Math.ceil(days.length / 7));
+ days.forEach((row, index) => {
+ const x = 54 + slot * (index + .5);
+ const height = valueOf(row) / peak * 176;
+ const detail = row.key + ' · ' + label('usageTotal') + ' ' + exact(row.totalTokens) + ' · ' + label('usageCalls') + ' ' + exact(row.modelCalls) + ' · ' + label('usageCacheRate') + ' ' + tokenUsageCacheRate(row);
+ const bar = element('rect', { x: x - Math.min(24, slot * .55) / 2, y: 194 - height, width: Math.min(24, slot * .55), height: Math.max(height, 1), rx: 3, class: 'token-usage-chart-bar', tabindex: 0, 'aria-label': detail });
+ bar.append(element('title', {}, detail));
+ for (const event of ['mouseenter', 'focus']) bar.addEventListener(event, () => { tooltip.textContent = detail; });
+ for (const event of ['mouseleave', 'blur']) bar.addEventListener(event, () => { tooltip.textContent = ui('chartHint'); });
+ svg.append(bar);
+ if (index % every === 0 || index === days.length - 1) {
+ svg.append(element('text', { x, y: 218, 'text-anchor': 'middle', class: 'token-usage-chart-label' }, row.key.slice(5)));
+ }
+ });
+ const plot = tokenUsageNode('div', 'token-usage-svg-wrap');
+ plot.append(svg);
+ chart.append(plot);
+ chart.append(tooltip);
+ if (!days.length) chart.append(tokenUsageNode('p', 'token-usage-empty', ui('noDailyData')));
+ chartLayout.append(chart);
+
+ const cache = tokenUsageNode('section', 'token-usage-chart-card token-usage-cache-card');
+ cache.append(tokenUsageNode('h4', '', ui('cacheComposition')));
+ const input = tokenUsageCount(summary.promptTokens);
+ const cached = Math.min(input, tokenUsageCount(summary.cachedTokens));
+ const ratio = input ? cached / input * 100 : 0;
+ const ring = tokenUsageNode('div', 'token-usage-cache-ring');
+ ring.style.setProperty('--cache-ratio', ratio + '%');
+ ring.append(tokenUsageNode('strong', '', tokenUsageCacheRate(summary)), tokenUsageNode('span', '', ui('cacheHit')));
+ cache.append(ring);
+ for (const [key, value, className] of [['usageCacheRead', cached, 'is-cached'], ['uncachedInput', input - cached, 'is-uncached']]) {
+ const line = tokenUsageNode('div', 'token-usage-cache-legend ' + className);
+ line.append(tokenUsageNode('span', '', key === 'uncachedInput' ? ui(key) : label(key)), tokenUsageNode('strong', '', exact(value)));
+ cache.append(line);
+ }
+ cache.append(tokenUsageNode('p', 'token-usage-chart-note', ui('cacheNote')));
+ chartLayout.append(cache);
+ host.append(chartLayout);
+
+ // Provider labels are untrusted: render all values as text or constructed
+ // nodes, never as HTML. Full precision is retained in every table.
+ const table = (titleKey, headings, rows, collapsed = false) => {
+ const section = tokenUsageNode(collapsed ? 'details' : 'section', 'token-usage-data-card');
+ const title = tokenUsageNode(collapsed ? 'summary' : 'h4', '', label(titleKey));
+ const wrap = tokenUsageNode('div', 'token-usage-table-wrap');
+ const grid = tokenUsageNode('table');
+ const caption = tokenUsageNode('caption', 'sr-only', label(titleKey));
+ const head = tokenUsageNode('thead');
+ const hr = tokenUsageNode('tr');
+ headings.forEach(key => { const th = tokenUsageNode('th', '', label(key)); th.scope = 'col'; hr.append(th); });
head.append(hr);
- const body = document.createElement('tbody');
+ const body = tokenUsageNode('tbody');
rows.forEach(values => {
- const tr = document.createElement('tr');
+ const tr = tokenUsageNode('tr');
values.forEach(value => {
- const td = document.createElement('td');
- td.textContent = String(value == null ? '' : value);
+ const td = tokenUsageNode('td');
+ if (value && value.nodeType) td.append(value);
+ else td.textContent = String(value == null ? '' : value);
tr.append(td);
});
body.append(tr);
@@ -162,36 +271,21 @@ function renderTokenUsageAnalysis(res) {
section.append(title, wrap);
host.append(section);
};
- const counts = row => [exact(row.promptTokens), exact(row.completionTokens), exact(row.cachedTokens),
- exact(row.cacheWriteTokens), exact(row.reasoningTokens), exact(row.totalTokens), exact(row.modelCalls)];
+ const counts = row => [exact(row.promptTokens), exact(row.completionTokens), exact(row.cachedTokens), exact(row.cacheWriteTokens), exact(row.reasoningTokens), exact(row.totalTokens), exact(row.modelCalls)];
const fields = ['usageInput', 'usageOutput', 'usageCacheRead', 'usageCacheWrite', 'usageReasoning', 'usageTotal', 'usageCalls'];
- table('usageByModel', ['usageModel', 'usageShare', ...fields], (res.byModel || []).map(row => [row.label || row.key,
- tokenUsageCount(res.summary.totalTokens) > 0 ? (tokenUsageCount(row.totalTokens) / tokenUsageCount(res.summary.totalTokens) * 100).toFixed(1) + '%' : '—', ...counts(row)]));
- const trendTitle = document.createElement('h4');
- trendTitle.textContent = label('usageTrend');
- const trend = document.createElement('div');
- trend.className = 'token-usage-trend';
- const days = (res.byDay || []).slice().reverse();
- const peak = Math.max(1, ...days.map(row => tokenUsageCount(row.totalTokens)));
- days.forEach(row => {
- const bar = document.createElement('div');
- bar.className = 'token-usage-day';
- const count = document.createElement('span');
- count.textContent = formatTokenUsageCompact(row.totalTokens);
- const fill = document.createElement('div');
- fill.className = 'token-usage-day-bar';
- fill.style.height = Math.max(1, tokenUsageCount(row.totalTokens) / peak * 90) + 'px';
- const date = document.createElement('span');
- date.textContent = String(row.key || '').slice(5);
- bar.title = row.key + ': ' + exact(row.totalTokens);
- bar.append(count, fill, date);
- trend.append(bar);
- });
- host.append(trendTitle, trend);
- table('usageByDay', ['usageDate', ...fields], (res.byDay || []).map(row => [row.key, ...counts(row)]));
+ table('usageByModel', ['usageModel', 'usageShare', ...fields], (res.byModel || []).map(row => {
+ const ratio = tokenUsageCount(summary.totalTokens) ? tokenUsageCount(row.totalTokens) / tokenUsageCount(summary.totalTokens) * 100 : 0;
+ const share = tokenUsageNode('div', 'token-usage-share');
+ share.append(tokenUsageNode('span', '', ratio.toFixed(1) + '%'));
+ const track = tokenUsageNode('span', 'token-usage-share-track');
+ const fill = tokenUsageNode('span'); fill.style.width = Math.min(100, ratio) + '%'; track.append(fill); share.append(track);
+ return [row.label || row.key, share, ...counts(row)];
+ }));
+ table('usageByDay', ['usageDate', ...fields], (res.byDay || []).map(row => [row.key, ...counts(row)]), true);
table('usageRecent', ['usageTime', 'usageModel', 'usageStatus', 'usageTotal', 'usageCalls'], (res.recent || []).map(row => {
const time = new Date(row.createdAt);
- return [Number.isFinite(time.getTime()) ? time.toLocaleString(window.__locale || 'zh-CN') : '—',
- row.model || '—', row.reason === 'final' ? label('usageFinal') : row.reason === 'partial' ? label('usagePartial') : (row.reason || '—'), exact(row.totalTokens), exact(row.modelCalls)];
+ const status = tokenUsageNode('span', 'token-usage-status', row.reason === 'final' ? label('usageFinal') : row.reason === 'partial' ? label('usagePartial') : (row.reason || '—'));
+ if (row.reason === 'final' || row.reason === 'partial') status.classList.add('is-' + row.reason);
+ return [Number.isFinite(time.getTime()) ? time.toLocaleString(window.__locale || 'zh-CN') : '—', row.model || '—', status, exact(row.totalTokens), exact(row.modelCalls)];
}));
}
diff --git a/web/templates/index.html b/web/templates/index.html
index 147d3cee..8698ffa3 100644
--- a/web/templates/index.html
+++ b/web/templates/index.html
@@ -39,7 +39,7 @@
}
})();
-
+
@@ -3642,8 +3642,8 @@
@@ -3652,8 +3652,9 @@
+
-
统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。模型按运行配置归类,切换模型的运行可能混合用量。
+
统计口径与说明
统计已记录的 Agent 运行中模型返回的用量,包括子 Agent。缓存读取和写入属于输入,推理属于输出,不重复加入总量。未返回或未采集的用量不在统计内;这不是供应商账单。模型按运行配置归类,切换模型的运行可能混合用量。
@@ -7023,7 +7024,7 @@
-
+