@@ -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 4/6] 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 5/6] 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 @@
-
+
From 4f0a3049cb071fd2178049f509d13c8b661b03a9 Mon Sep 17 00:00:00 2001
From: Sycun <165354365+Sycun@users.noreply.github.com>
Date: Sun, 11 Oct 2026 13:23:43 +0800
Subject: [PATCH 6/6] fix: recover summary limits and sanitize agentic tool
history
---
...ool_call_arguments_sanitizer_middleware.go | 75 ++++++
...all_arguments_sanitizer_middleware_test.go | 214 ++++++++++++++++++
...eino_agentic_chat_model_tail_middleware.go | 7 +-
...agentic_chat_model_tail_middleware_test.go | 6 +-
.../multiagent/eino_summarize_model_guard.go | 65 +++++-
.../eino_summarize_model_guard_test.go | 18 +-
.../multiagent/eino_summarize_payload_test.go | 117 ++++++++++
7 files changed, 488 insertions(+), 14 deletions(-)
create mode 100644 internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware.go
create mode 100644 internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware_test.go
diff --git a/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware.go b/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware.go
new file mode 100644
index 00000000..ad204bf3
--- /dev/null
+++ b/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware.go
@@ -0,0 +1,75 @@
+package multiagent
+
+import (
+ "context"
+
+ "github.com/cloudwego/eino/adk"
+ "github.com/cloudwego/eino/schema"
+ "go.uber.org/zap"
+)
+
+// Apply the classic history repair to native function-call blocks too. Providers
+// may parse arguments embedded in otherwise valid request JSON and reject the
+// next turn if a previous model response contained truncated arguments. Repair
+// only historical input; never repair or execute an incomplete new tool call.
+type agenticToolCallArgumentsSanitizerMiddleware struct {
+ *adk.TypedBaseChatModelAgentMiddleware[*schema.AgenticMessage]
+ logger *zap.Logger
+ phase string
+}
+
+func newAgenticToolCallArgumentsSanitizerMiddleware(logger *zap.Logger, phase string) adk.TypedChatModelAgentMiddleware[*schema.AgenticMessage] {
+ return &agenticToolCallArgumentsSanitizerMiddleware{
+ TypedBaseChatModelAgentMiddleware: &adk.TypedBaseChatModelAgentMiddleware[*schema.AgenticMessage]{},
+ logger: logger, phase: phase,
+ }
+}
+
+func (m *agenticToolCallArgumentsSanitizerMiddleware) BeforeModelRewriteState(
+ ctx context.Context, state *adk.TypedChatModelAgentState[*schema.AgenticMessage],
+ _ *adk.TypedModelContext[*schema.AgenticMessage],
+) (context.Context, *adk.TypedChatModelAgentState[*schema.AgenticMessage], error) {
+ if m == nil || state == nil {
+ return ctx, state, nil
+ }
+ var out []*schema.AgenticMessage
+ repaired := 0
+ for i, msg := range state.Messages {
+ if msg == nil || msg.Role != schema.AgenticRoleTypeAssistant {
+ continue
+ }
+ var blocks []*schema.ContentBlock
+ for j, block := range msg.ContentBlocks {
+ if block == nil || block.FunctionToolCall == nil || validToolArgumentsJSONObject(block.FunctionToolCall.Arguments) {
+ continue
+ }
+ if blocks == nil {
+ blocks = append([]*schema.ContentBlock(nil), msg.ContentBlocks...)
+ }
+ clonedBlock := *block
+ clonedCall := *block.FunctionToolCall
+ clonedCall.Arguments = repairedMalformedToolArguments
+ clonedBlock.FunctionToolCall = &clonedCall
+ blocks[j] = &clonedBlock
+ repaired++
+ }
+ if blocks == nil {
+ continue
+ }
+ if out == nil {
+ out = append([]*schema.AgenticMessage(nil), state.Messages...)
+ }
+ clonedMessage := *msg
+ clonedMessage.ContentBlocks = blocks
+ out[i] = &clonedMessage
+ }
+ if repaired == 0 {
+ return ctx, state, nil
+ }
+ if m.logger != nil {
+ m.logger.Warn("eino agentic malformed tool-call arguments repaired before model call", zap.String("phase", m.phase), zap.Int("repaired_calls", repaired))
+ }
+ clonedState := *state
+ clonedState.Messages = out
+ return ctx, &clonedState, nil
+}
diff --git a/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware_test.go b/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware_test.go
new file mode 100644
index 00000000..e1878e02
--- /dev/null
+++ b/internal/multiagent/agentic_tool_call_arguments_sanitizer_middleware_test.go
@@ -0,0 +1,214 @@
+package multiagent
+
+import (
+ "context"
+ "encoding/json"
+ "errors"
+ "fmt"
+ "io"
+ "net/http"
+ "net/http/httptest"
+ "strings"
+ "testing"
+
+ "cyberstrike-ai/internal/config"
+ "github.com/cloudwego/eino/adk"
+ "github.com/cloudwego/eino/schema"
+)
+
+func TestAgenticToolArgumentsSanitizerPreservesHistory(t *testing.T) {
+ for _, args := range []string{`{"command":"unterminated`, `[]`, `null`, ``, `{"command":`} {
+ t.Run(args, func(t *testing.T) {
+ good := schema.NewContentBlock(&schema.FunctionToolCall{CallID: "good", Name: "exec", Arguments: `{"command":"pwd"}`})
+ bad := schema.NewContentBlock(&schema.FunctionToolCall{CallID: "bad", Name: "exec", Arguments: args})
+ text := schema.NewContentBlock(&schema.AssistantGenText{Text: "keep findings"})
+ user := schema.UserAgenticMessage("latest instruction")
+ result := schema.UserAgenticMessage("execution failed")
+ msg := &schema.AgenticMessage{Role: schema.AgenticRoleTypeAssistant, ContentBlocks: []*schema.ContentBlock{nil, text, good, bad}}
+ state := &adk.TypedChatModelAgentState[*schema.AgenticMessage]{Messages: []*schema.AgenticMessage{nil, msg, result, user}}
+ mw := newAgenticToolCallArgumentsSanitizerMiddleware(nil, "test")
+ _, out, err := mw.BeforeModelRewriteState(context.Background(), state, nil)
+ if err != nil {
+ t.Fatal(err)
+ }
+ if out == state || out.Messages[1] == msg || out.Messages[1].ContentBlocks[3] == bad {
+ t.Fatal("repair must copy history")
+ }
+ repaired := out.Messages[1].ContentBlocks[3].FunctionToolCall
+ if repaired.Arguments != `{}` || repaired.Name != "exec" || repaired.CallID != "bad" {
+ t.Fatalf("repair changed call identity: %+v", repaired)
+ }
+ if bad.FunctionToolCall.Arguments != args {
+ t.Fatal("mutated original arguments")
+ }
+ if out.Messages[1].ContentBlocks[1] != text || out.Messages[1].ContentBlocks[2] != good || out.Messages[2] != result || out.Messages[3] != user {
+ t.Fatal("changed unrelated history")
+ }
+ _, unchanged, err := mw.BeforeModelRewriteState(context.Background(), out, nil)
+ if err != nil || unchanged != out {
+ t.Fatal("valid history should remain unchanged")
+ }
+ })
+ }
+}
+
+// A real SDK round trip reproduces a gateway that parses tool argument strings
+// on subsequent turns: valid outer JSON alone does not prevent this HTTP 400.
+func TestAgenticToolArgumentsSanitizerPreventsMultiTurnHTTP400(t *testing.T) {
+ server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+ var body struct {
+ Messages []struct {
+ Role string `json:"role"`
+ ToolCalls []struct {
+ ID string `json:"id"`
+ Function struct {
+ Arguments string `json:"arguments"`
+ } `json:"function"`
+ } `json:"tool_calls"`
+ } `json:"messages"`
+ }
+ if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+ t.Error(err)
+ w.WriteHeader(400)
+ return
+ }
+ calls := 0
+ for _, msg := range body.Messages {
+ for _, call := range msg.ToolCalls {
+ calls++
+ if !validToolArgumentsJSONObject(call.Function.Arguments) {
+ w.Header().Set("Content-Type", "application/json")
+ w.WriteHeader(400)
+ fmt.Fprint(w, `{"error":{"message":"Unterminated string starting at: line 1 column 13 (char 12)","type":"invalid_request_error"}}`)
+ return
+ }
+ if call.ID != "broken" || call.Function.Arguments != `{}` {
+ t.Errorf("unexpected history call: %+v", call)
+ }
+ }
+ }
+ if calls != 1 {
+ t.Errorf("history calls=%d, want 1", calls)
+ }
+ w.Header().Set("Content-Type", "text/event-stream")
+ fmt.Fprint(w, "data: {\"id\":\"test\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":\"continued\"},\"finish_reason\":null}]}\n\ndata: {\"id\":\"test\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":\"stop\"}]}\n\ndata: [DONE]\n\n")
+ }))
+ defer server.Close()
+ ctx := context.Background()
+ base, err := newEinoAgenticChatModelFactory(server.Client(), nil, nil)(ctx, config.OpenAIConfig{Provider: "openai", APIKey: "test-key", BaseURL: server.URL, Model: "space-bunny-free"}, einoModelModeNormal)
+ if err != nil {
+ t.Fatal(err)
+ }
+ broken := schema.AssistantMessage("", []schema.ToolCall{{ID: "broken", Type: "function", Function: schema.FunctionCall{Name: "exec", Arguments: `{"command":"unterminated`}}})
+ input := []*schema.Message{schema.UserMessage("start"), broken, schema.ToolMessage("Invalid JSON arguments; tool was not executed", "broken"), schema.UserMessage("continue")}
+ for _, repair := range []bool{false, true} {
+ t.Run(fmt.Sprint(repair), func(t *testing.T) {
+ var handlers []adk.TypedChatModelAgentMiddleware[*schema.AgenticMessage]
+ if repair {
+ handlers = appendEinoAgenticChatModelTailMiddlewares(nil, einoChatModelTailConfig{phase: "test"})
+ }
+ agent, err := newEinoAgenticChatModelAgentAdapter(ctx, einoAgenticChatModelAgentConfig{Name: "test", Model: base, Handlers: handlers})
+ if err != nil {
+ t.Fatal(err)
+ }
+ it := agent.Run(ctx, &adk.AgentInput{Messages: input, EnableStreaming: true})
+ var runErr error
+ var answer strings.Builder
+ for {
+ ev, ok := it.Next()
+ if !ok {
+ break
+ }
+ if ev.Err != nil {
+ runErr = ev.Err
+ break
+ }
+ if ev.Output != nil && ev.Output.MessageOutput != nil && ev.Output.MessageOutput.MessageStream != nil {
+ stream := ev.Output.MessageOutput.MessageStream
+ for {
+ msg, err := stream.Recv()
+ if err != nil {
+ if !errors.Is(err, io.EOF) {
+ runErr = err
+ }
+ break
+ }
+ if msg != nil {
+ answer.WriteString(msg.Content)
+ }
+ }
+ stream.Close()
+ }
+ }
+ if repair && runErr != nil {
+ t.Fatalf("repaired history rejected: %v", runErr)
+ }
+ if repair && !strings.Contains(answer.String(), "continued") {
+ t.Fatalf("agent did not continue: %q", answer.String())
+ }
+ if !repair && runErr == nil {
+ t.Fatal("expected HTTP 400 without sanitizer")
+ }
+ if broken.ToolCalls[0].Function.Arguments != `{"command":"unterminated` {
+ t.Fatal("original history mutated")
+ }
+ })
+ }
+}
+
+// Summarization makes its own model call and can rewrite retained history, so
+// guard both its input and the final model input rather than just one boundary.
+type agenticSummaryArgumentsProbe struct {
+ *adk.TypedBaseChatModelAgentMiddleware[*schema.AgenticMessage]
+ checked bool
+}
+
+func (p *agenticSummaryArgumentsProbe) BeforeModelRewriteState(ctx context.Context, state *adk.TypedChatModelAgentState[*schema.AgenticMessage], _ *adk.TypedModelContext[*schema.AgenticMessage]) (context.Context, *adk.TypedChatModelAgentState[*schema.AgenticMessage], error) {
+ for _, msg := range state.Messages {
+ for _, call := range agenticFunctionToolCalls(msg) {
+ if !validToolArgumentsJSONObject(call.Arguments) {
+ return ctx, state, fmt.Errorf("invalid arguments reached summarization")
+ }
+ p.checked = true
+ }
+ }
+ out := *state
+ out.Messages = append([]*schema.AgenticMessage(nil), state.Messages...)
+ for i, msg := range out.Messages {
+ if len(agenticFunctionToolCalls(msg)) == 0 {
+ continue
+ }
+ calls := []*schema.FunctionToolCall{{CallID: "broken", Name: "exec", Arguments: `{"command":"truncated`}}
+ out.Messages[i] = cloneAgenticMessageWithCalls(msg, calls)
+ }
+ return ctx, &out, nil
+}
+
+func TestAgenticToolArgumentsSanitizerAroundSummarization(t *testing.T) {
+ probe := &agenticSummaryArgumentsProbe{TypedBaseChatModelAgentMiddleware: &adk.TypedBaseChatModelAgentMiddleware[*schema.AgenticMessage]{}}
+ history := EinoMessagesToAgentic([]*schema.Message{
+ schema.AssistantMessage("", []schema.ToolCall{{ID: "broken", Type: "function", Function: schema.FunctionCall{Name: "exec", Arguments: `{"command":"truncated`}}}),
+ schema.ToolMessage("invalid JSON; not executed", "broken"),
+ schema.UserMessage("continue"),
+ })
+ state := &adk.TypedChatModelAgentState[*schema.AgenticMessage]{Messages: history}
+ handlers := appendEinoAgenticChatModelTailMiddlewares(nil, einoChatModelTailConfig{agenticSummarization: probe})
+ ctx := context.Background()
+ for _, handler := range handlers {
+ var err error
+ ctx, state, err = handler.BeforeModelRewriteState(ctx, state, nil)
+ if err != nil {
+ t.Fatal(err)
+ }
+ }
+ if !probe.checked {
+ t.Fatal("summary probe did not inspect retained call")
+ }
+ calls := agenticFunctionToolCalls(state.Messages[0])
+ if len(calls) != 1 || calls[0].Arguments != `{}` {
+ t.Fatalf("final input contains malformed call: %+v", calls)
+ }
+ if agenticFunctionToolCalls(history[0])[0].Arguments != `{"command":"truncated` {
+ t.Fatal("mutated original history")
+ }
+}
diff --git a/internal/multiagent/eino_agentic_chat_model_tail_middleware.go b/internal/multiagent/eino_agentic_chat_model_tail_middleware.go
index 738a9b27..7ee7f3eb 100644
--- a/internal/multiagent/eino_agentic_chat_model_tail_middleware.go
+++ b/internal/multiagent/eino_agentic_chat_model_tail_middleware.go
@@ -10,19 +10,20 @@ import (
)
// appendEinoAgenticChatModelTailMiddlewares appends protocol-neutral handlers for
-// TypedChatModelAgent[*schema.AgenticMessage]. Classic ReAct history repair
-// handlers stay on the schema.Message path because AgenticMessage has native
-// content blocks for function calls/results.
+// TypedChatModelAgent[*schema.AgenticMessage]. History repair operates
+// directly on native function-call/result blocks without converting protocols.
func appendEinoAgenticChatModelTailMiddlewares(
handlers []adk.TypedChatModelAgentMiddleware[*schema.AgenticMessage],
cfg einoChatModelTailConfig,
) []adk.TypedChatModelAgentMiddleware[*schema.AgenticMessage] {
handlers = append(handlers, newAgenticSystemMessageNormalizerMiddleware(cfg.logger, cfg.phase))
handlers = append(handlers, newAgenticContinuationUserDedupMiddleware(cfg.logger, cfg.phase))
+ handlers = append(handlers, newAgenticToolCallArgumentsSanitizerMiddleware(cfg.logger, cfg.phase+"_pre_summarization"))
if cfg.agenticSummarization != nil {
handlers = append(handlers, newAgenticToolPairReconcilerMiddleware(cfg.logger, cfg.phase+"_pre_summarization"))
handlers = append(handlers, cfg.agenticSummarization)
}
+ handlers = append(handlers, newAgenticToolCallArgumentsSanitizerMiddleware(cfg.logger, cfg.phase))
handlers = append(handlers, newAgenticToolPairReconcilerMiddleware(cfg.logger, cfg.phase))
if !cfg.skipOrphanPruner {
handlers = append(handlers, newAgenticOrphanToolPrunerMiddleware(cfg.logger, cfg.phase))
diff --git a/internal/multiagent/eino_agentic_chat_model_tail_middleware_test.go b/internal/multiagent/eino_agentic_chat_model_tail_middleware_test.go
index 9b6d9d5c..22e135aa 100644
--- a/internal/multiagent/eino_agentic_chat_model_tail_middleware_test.go
+++ b/internal/multiagent/eino_agentic_chat_model_tail_middleware_test.go
@@ -106,8 +106,8 @@ func TestAppendEinoAgenticChatModelTailMiddlewares(t *testing.T) {
phase: "agentic",
trace: holder,
})
- // system + continuation + reconciler + orphan_pruner + trace
- if len(handlers) != 5 {
- t.Fatalf("handlers = %d, want system + continuation + reconciler + orphan_pruner + trace", len(handlers))
+ // system + continuation + two argument sanitizers + reconciler + orphan_pruner + trace
+ if len(handlers) != 7 {
+ t.Fatalf("handlers = %d, want system + continuation + two argument sanitizers + reconciler + orphan_pruner + trace", len(handlers))
}
}
diff --git a/internal/multiagent/eino_summarize_model_guard.go b/internal/multiagent/eino_summarize_model_guard.go
index c0b9757d..d735acf3 100644
--- a/internal/multiagent/eino_summarize_model_guard.go
+++ b/internal/multiagent/eino_summarize_model_guard.go
@@ -50,6 +50,20 @@ func einoSummarizationModelRawErrorText(err error) (string, bool) {
return strings.TrimSpace(summaryErr.err.Error()), true
}
+// Output-limit failures need a different prompt, rather than repeating the same
+// overlong summary or accepting truncated text as replacement conversation history.
+type einoSummaryOutputLimitError struct{ err error }
+
+func (e *einoSummaryOutputLimitError) Error() string { return e.err.Error() }
+func (e *einoSummaryOutputLimitError) Unwrap() error { return e.err }
+
+const conciseSummaryRetryInstruction = `The previous summarization request exhausted its output token budget. Generate a new, substantially shorter, complete summary from the original conversation above. Omit the
block and output only .... Preserve authorization, user constraints, confirmed findings, essential technical details, current progress and next steps. Merge repetitions and summarize long logs and asset lists. Do not repeat the full transcript or call tools. Finish all sections and the closing tag within the available output budget.`
+
+func shouldRetryConciseSummary(ctx context.Context, err error) bool {
+ var limitErr *einoSummaryOutputLimitError
+ return ctx.Err() == nil && errors.As(err, &limitErr)
+}
+
type nonEmptySummaryChatModel struct {
base model.BaseChatModel
}
@@ -59,6 +73,16 @@ func newNonEmptySummaryChatModel(base model.BaseChatModel) model.BaseChatModel {
}
func (m *nonEmptySummaryChatModel) Generate(ctx context.Context, input []*schema.Message, opts ...model.Option) (*schema.Message, error) {
+ out, err := m.generateOnce(ctx, input, opts...)
+ if !shouldRetryConciseSummary(ctx, err) {
+ return out, err
+ }
+ // Copy the slice: retry instructions must not mutate caller-owned history.
+ retryInput := append(append([]*schema.Message(nil), input...), schema.UserMessage(conciseSummaryRetryInstruction))
+ return m.generateOnce(ctx, retryInput, opts...)
+}
+
+func (m *nonEmptySummaryChatModel) generateOnce(ctx context.Context, input []*schema.Message, opts ...model.Option) (*schema.Message, error) {
if err := ctx.Err(); err != nil {
return nil, newEinoSummarizationModelError(err)
}
@@ -70,11 +94,15 @@ func (m *nonEmptySummaryChatModel) Generate(ctx context.Context, input []*schema
if err != nil {
return nil, newEinoSummarizationModelError(err)
}
+ completionErr := validateClassicSummaryCompletion(out)
+ if shouldRetryConciseSummary(ctx, completionErr) {
+ return nil, newEinoSummarizationModelError(completionErr)
+ }
if strings.TrimSpace(classicAssistantTextContent(out)) == "" {
return nil, newEinoSummarizationModelError(fmt.Errorf("summary content is empty: %s", classicSummaryEmptyDiagnostics(out)))
}
- if err := validateClassicSummaryCompletion(out); err != nil {
- return nil, newEinoSummarizationModelError(err)
+ if completionErr != nil {
+ return nil, newEinoSummarizationModelError(completionErr)
}
return out, nil
}
@@ -92,6 +120,16 @@ func newNonEmptyAgenticSummaryModel(base model.BaseModel[*schema.AgenticMessage]
}
func (m *nonEmptyAgenticSummaryModel) Generate(ctx context.Context, input []*schema.AgenticMessage, opts ...model.Option) (*schema.AgenticMessage, error) {
+ out, err := m.generateOnce(ctx, input, opts...)
+ if !shouldRetryConciseSummary(ctx, err) {
+ return out, err
+ }
+ // Copy the slice: retry instructions must not mutate caller-owned history.
+ retryInput := append(append([]*schema.AgenticMessage(nil), input...), schema.UserAgenticMessage(conciseSummaryRetryInstruction))
+ return m.generateOnce(ctx, retryInput, opts...)
+}
+
+func (m *nonEmptyAgenticSummaryModel) generateOnce(ctx context.Context, input []*schema.AgenticMessage, opts ...model.Option) (*schema.AgenticMessage, error) {
if err := ctx.Err(); err != nil {
return nil, newEinoSummarizationModelError(err)
}
@@ -103,11 +141,15 @@ func (m *nonEmptyAgenticSummaryModel) Generate(ctx context.Context, input []*sch
if err != nil {
return nil, newEinoSummarizationModelError(err)
}
+ completionErr := validateAgenticSummaryCompletion(out)
+ if shouldRetryConciseSummary(ctx, completionErr) {
+ return nil, newEinoSummarizationModelError(completionErr)
+ }
if strings.TrimSpace(agenticAssistantTextContent(out)) == "" {
return nil, newEinoSummarizationModelError(fmt.Errorf("summary content is empty: %s", agenticSummaryEmptyDiagnostics(out)))
}
- if err := validateAgenticSummaryCompletion(out); err != nil {
- return nil, newEinoSummarizationModelError(err)
+ if completionErr != nil {
+ return nil, newEinoSummarizationModelError(completionErr)
}
return out, nil
}
@@ -278,6 +320,9 @@ func validateClassicSummaryCompletion(msg *schema.Message) error {
if msg.ResponseMeta != nil {
reason = msg.ResponseMeta.FinishReason
}
+ if reason == "length" && len(msg.ToolCalls) == 0 {
+ return &einoSummaryOutputLimitError{err: fmt.Errorf("summary did not complete: finish_reason=%q tool_calls=%d", reason, len(msg.ToolCalls))}
+ }
if reason != "stop" || len(msg.ToolCalls) != 0 {
return fmt.Errorf("summary did not complete: finish_reason=%q tool_calls=%d", reason, len(msg.ToolCalls))
}
@@ -290,13 +335,21 @@ func validateAgenticSummaryCompletion(msg *schema.AgenticMessage) error {
if ext.FinishReason == "stop" {
return nil
}
- return fmt.Errorf("summary did not complete: openai chat finish_reason=%q", ext.FinishReason)
+ err := fmt.Errorf("summary did not complete: openai chat finish_reason=%q", ext.FinishReason)
+ if ext.FinishReason == "length" {
+ return &einoSummaryOutputLimitError{err: err}
+ }
+ return err
}
if ext := meta.ClaudeExtension; ext != nil {
if ext.StopReason == "end_turn" {
return nil
}
- return fmt.Errorf("summary did not complete: claude stop_reason=%q", ext.StopReason)
+ err := fmt.Errorf("summary did not complete: claude stop_reason=%q", ext.StopReason)
+ if ext.StopReason == "max_tokens" {
+ return &einoSummaryOutputLimitError{err: err}
+ }
+ return err
}
if ext := meta.OpenAIExtension; ext != nil {
if ext.Status == schemaopenai.ResponseStatusCompleted && ext.Error == nil && ext.IncompleteDetails == nil {
diff --git a/internal/multiagent/eino_summarize_model_guard_test.go b/internal/multiagent/eino_summarize_model_guard_test.go
index 8fe2da2f..7cb562b3 100644
--- a/internal/multiagent/eino_summarize_model_guard_test.go
+++ b/internal/multiagent/eino_summarize_model_guard_test.go
@@ -8,6 +8,7 @@ import (
"net/http"
"net/http/httptest"
"strings"
+ "sync/atomic"
"testing"
"time"
@@ -208,13 +209,15 @@ func TestSummaryStreamFailuresDoNotReturnPartialSummary(t *testing.T) {
}
func TestClaudeSummaryLargeBudgetStreamsThroughNativeSDK(t *testing.T) {
- for _, mode := range []string{"complete", "truncated", "early_eof", "cancel_read"} {
+ for _, mode := range []string{"complete", "recovers", "truncated", "early_eof", "cancel_read"} {
t.Run(mode, func(t *testing.T) {
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
started := make(chan struct{})
+ var requests atomic.Int32
server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+ request := requests.Add(1)
var body struct {
Stream bool `json:"stream"`
MaxTokens int `json:"max_tokens"`
@@ -240,6 +243,10 @@ func TestClaudeSummaryLargeBudgetStreamsThroughNativeSDK(t *testing.T) {
`{"type":"message_stop"}`,
}
switch mode {
+ case "recovers":
+ if request == 1 {
+ events[5] = strings.ReplaceAll(events[5], "end_turn", "max_tokens")
+ }
case "truncated":
events[5] = strings.ReplaceAll(events[5], "end_turn", "max_tokens")
case "early_eof", "cancel_read":
@@ -283,7 +290,14 @@ func TestClaudeSummaryLargeBudgetStreamsThroughNativeSDK(t *testing.T) {
defer timer.Stop()
}
out, err := newNonEmptyAgenticSummaryModel(native).Generate(ctx, input, opts...)
- if mode != "complete" {
+ wantRequests := int32(1)
+ if mode == "recovers" || mode == "truncated" {
+ wantRequests = 2
+ }
+ if requests.Load() != wantRequests {
+ t.Fatalf("requests=%d, want %d", requests.Load(), wantRequests)
+ }
+ if mode != "complete" && mode != "recovers" {
if out != nil || err == nil {
t.Fatalf("accepted partial summary: out=%+v err=%v", out, err)
}
diff --git a/internal/multiagent/eino_summarize_payload_test.go b/internal/multiagent/eino_summarize_payload_test.go
index 186b7793..21e7e17c 100644
--- a/internal/multiagent/eino_summarize_payload_test.go
+++ b/internal/multiagent/eino_summarize_payload_test.go
@@ -3,9 +3,11 @@ package multiagent
import (
"context"
"encoding/json"
+ "fmt"
"net/http"
"net/http/httptest"
"strings"
+ "sync/atomic"
"testing"
"cyberstrike-ai/internal/config"
@@ -148,3 +150,118 @@ func TestEinoSummarizationModelOptionsSetOnlyMaxCompletionTokens(t *testing.T) {
t.Fatalf("max_completion_tokens = %#v, want %d", body["max_completion_tokens"], outputReserve)
}
}
+
+// Exercise both production factories and their real SDK options, not just a
+// fake model: a truncated summary must be replaced only by a complete retry.
+func TestSummaryOutputLimitConciseRetry(t *testing.T) {
+ for _, kind := range []string{"classic", "agentic"} {
+ for _, tc := range []struct {
+ name string
+ firstReason string
+ retryReason string
+ firstText string
+ wantCalls int
+ wantErr bool
+ }{
+ {"complete", "stop", "", "complete summary", 1, false},
+ {"recovers", "length", "stop", "truncated summary", 2, false},
+ {"reasoning_only_recovers", "length", "stop", "", 2, false},
+ {"still_truncated", "length", "length", "truncated summary", 2, true},
+ {"retry_filtered", "length", "content_filter", "truncated summary", 2, true},
+ {"filtered", "content_filter", "", "filtered summary", 1, true},
+ {"missing_completion", "", "", "partial summary", 1, true},
+ } {
+ t.Run(kind+"/"+tc.name, func(t *testing.T) {
+ var calls atomic.Int32
+ bodies := make(chan map[string]any, 3)
+ server := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+ n := calls.Add(1)
+ var body map[string]any
+ if err := json.NewDecoder(r.Body).Decode(&body); err != nil {
+ t.Errorf("decode request: %v", err)
+ w.WriteHeader(400)
+ return
+ }
+ bodies <- body
+ if r.Header.Get("X-CyberStrike-Summarization") != "1" {
+ t.Error("missing summary request header")
+ }
+ text, reason := tc.firstText, tc.firstReason
+ if n > 1 {
+ text, reason = "complete retry summary", tc.retryReason
+ }
+ w.Header().Set("Content-Type", "text/event-stream")
+ fmt.Fprintf(w, "data: {\"id\":\"test\",\"choices\":[{\"index\":0,\"delta\":{\"role\":\"assistant\",\"content\":%q},\"finish_reason\":null}]}\n\n", text)
+ fmt.Fprintf(w, "data: {\"id\":\"test\",\"choices\":[{\"index\":0,\"delta\":{},\"finish_reason\":%q}]}\n\n", reason)
+ fmt.Fprint(w, "data: [DONE]\n\n")
+ }))
+ defer server.Close()
+ oa := config.OpenAIConfig{Provider: "openai", APIKey: "test-key", BaseURL: server.URL, Model: "deepseek-chat", MaxCompletionTokens: 128}
+ const reserve = 512
+ opts := newEinoSummarizationModelOptions(reserve, oa.Model, kind, &oa, nil)
+ ctx := context.Background()
+ var err error
+ var text string
+ if kind == "classic" {
+ base, modelErr := newEinoToolCallingChatModelFactory(server.Client(), nil, nil)(ctx, oa, einoModelModeNormal)
+ if modelErr != nil {
+ t.Fatal(modelErr)
+ }
+ input := []*schema.Message{schema.UserMessage("original conversation")}
+ out, genErr := newNonEmptySummaryChatModel(base).Generate(ctx, input, opts...)
+ err = genErr
+ text = classicAssistantTextContent(out)
+ if len(input) != 1 || input[0].Content != "original conversation" {
+ t.Fatal("mutated original history")
+ }
+ } else {
+ base, modelErr := newEinoAgenticChatModelFactory(server.Client(), nil, nil)(ctx, oa, einoModelModeNormal)
+ if modelErr != nil {
+ t.Fatal(modelErr)
+ }
+ input := []*schema.AgenticMessage{schema.UserAgenticMessage("original conversation")}
+ out, genErr := newNonEmptyAgenticSummaryModel(base).Generate(ctx, input, opts...)
+ err = genErr
+ text = agenticAssistantTextContent(out)
+ if len(input) != 1 {
+ t.Fatal("mutated original history")
+ }
+ }
+ if (err != nil) != tc.wantErr {
+ t.Fatalf("error = %v, wantErr = %v", err, tc.wantErr)
+ }
+ if tc.wantErr && text != "" {
+ t.Fatalf("accepted partial summary %q", text)
+ }
+ if !tc.wantErr && tc.wantCalls == 2 && text != "complete retry summary" {
+ t.Fatalf("summary = %q", text)
+ }
+ if int(calls.Load()) != tc.wantCalls {
+ t.Fatalf("calls = %d, want %d", calls.Load(), tc.wantCalls)
+ }
+ for i := 0; i < tc.wantCalls; i++ {
+ body := <-bodies
+ if body["max_completion_tokens"] != float64(reserve) {
+ t.Fatalf("output budget changed: %#v", body)
+ }
+ if _, ok := body["max_tokens"]; ok {
+ t.Fatal("duplicate output limits")
+ }
+ if _, ok := body["reasoning_effort"]; ok {
+ t.Fatal("reasoning enabled for summary")
+ }
+ msgs := body["messages"].([]any)
+ if i == 1 {
+ last := msgs[len(msgs)-1].(map[string]any)
+ if last["role"] != "user" || !strings.Contains(fmt.Sprint(last["content"]), conciseSummaryRetryInstruction) {
+ t.Fatalf("missing concise retry instruction: %#v", last)
+ }
+ if strings.Contains(fmt.Sprint(msgs), "truncated summary") {
+ t.Fatal("partial response leaked into retry history")
+ }
+ }
+ }
+ })
+ }
+ }
+}