dsh-recent-usage-metrics 0.3.0 → 0.3.2

package/CHANGELOG.md

@@ -1,3 +1,22 @@
+## 0.3.2
+
+- 修复：速度列的悬浮提示常常拿不到模型名，或显示成别的模型。
+  原来从统计折叠的 `request/header` 事件推断，但那种事件只在模型或工具集变化时才写——
+  真实会话里 3139 次请求只对应 24 条，覆盖率约 1%，其余步骤只能借用几小时前的旧值。
+- 改为读轨迹域的 assistant 节点：它把 `assistant/message.source` 原样复制成
+  `providerMetadata`，每步都有，是客户端半能拿到的唯一逐步事实。
+- 没有轨迹节点的步骤保持空值，不再借用旧 header 猜测。
+
+## 0.3.1
+
+- 修复：切换模型后的第一步，抽屉速度列的悬浮提示显示了上一个模型。
+  `request/header` 写在它自己的 `step/start` 之后约 4 毫秒，只按「早于该步开始的最近一条」
+  匹配会漏掉它，退回上一次请求的模型。现在先在该步到下一起点之间找，找不到才回退。
+  在 3119 步的真实日志上，旧规则命中 99.8%，新规则 100%。
+
+- 说明：`trae` 等 provider 不单独上报 `cacheReadTokens`，而是并入 `inputTokens`。
+  这类行没有缓存命中率可算，输出 Token 列的提示会显示破折号——这是数据源缺失，不是漏算。
+
 # 更新记录
 
 ## 0.3.0

package/client/client.js

@@ -1172,42 +1172,31 @@ window.__ModuleLoader__.load({
     /**
      * Which model answered each step, keyed `turn:step`.
      *
-     * The fold does not put a provider/model on a step — `stepMetrics` carries only derived
-     * figures, and an assistant chat node carries only its usage and timings. The model is
-     * recorded once per routed request as a `request/header` event row on the turn, so a step
-     * is attributed to the newest header that precedes it.
+     * Read from the Trajectory domain's assistant nodes, which carry `providerMetadata` copied
+     * straight from `assistant/message.source`. That is the only per-step source of truth the
+     * client half can reach:
      *
-     * Verified against the log: on a real session the newest preceding header matched the
-     * `assistant/message.source` of every one of 40 sampled steps. Headers are per-routed-
-     * request, so several consecutive steps share one, and a model switch starts a new one.
+     * - The statistics fold puts no provider/model on a step, and its `request-header` rows are
+     *   written only when the routed model or tool set CHANGES — 24 of them for 3139 requests in
+     *   a real session, so they describe about 1% of steps and mislabel the rest.
+     * - The Chat snapshot's assistant nodes drop the source entirely.
+     *
+     * A compaction is not covered here: it has its own `compaction.model`.
      */
-    function modelIndexFromStats(statsSnapshot) {
-      const turns = statsSnapshot?.turns
+    function modelIndexFromTrajectory(trajectorySnapshot) {
       const index = new Map()
-      if (!Array.isArray(turns)) return index
-      for (const turn of turns) {
-        if (!Array.isArray(turn.steps)) continue
-        const headers = []
-        if (Array.isArray(turn.events)) {
-          for (const event of turn.events) {
-            if (event?.kind !== 'request-header') continue
-            if (typeof event.model !== 'string' && typeof event.provider !== 'string') continue
-            headers.push({ time: numberOrNull(event.time) ?? 0, provider: event.provider ?? null, model: event.model ?? null })
-          }
-          headers.sort((left, right) => left.time - right.time)
-        }
-        if (headers.length === 0) continue
-        for (const step of turn.steps) {
-          const at = numberOrNull(step.startTime)
-          if (at === null || typeof step.step !== 'number') continue
-          let chosen = null
-          for (const header of headers) {
-            if (header.time <= at) chosen = header
-            else break
-          }
-          if (chosen === null) continue
-          index.set(`${turn.turn}:${step.step}`, chosen)
-        }
+      const nodes = trajectorySnapshot?.eventNodes
+      if (!Array.isArray(nodes)) return index
+      for (const node of nodes) {
+        if (node === null || typeof node !== 'object') continue
+        if (node.kind !== 'assistant') continue
+        const meta = node.providerMetadata
+        if (meta === null || typeof meta !== 'object') continue
+        const model = typeof meta.model === 'string' && meta.model !== '' ? meta.model : null
+        const provider = typeof meta.provider === 'string' && meta.provider !== '' ? meta.provider : null
+        if (model === null && provider === null) continue
+        if (typeof node.turn !== 'number' || typeof node.step !== 'number') continue
+        index.set(`${node.turn}:${node.step}`, { provider, model })
       }
       return index
     }
@@ -1265,9 +1254,8 @@ window.__ModuleLoader__.load({
      * *after* selection: capping here at ten and then dropping the live step left the drawer
      * showing nine rows for as long as a request was streaming.
      */
-    function historyFromStats(statsSnapshot) {
+    function historyFromStats(statsSnapshot, models) {
       const steps = statsSteps(statsSnapshot)
-      const models = modelIndexFromStats(statsSnapshot)
       const rows = []
       for (const entry of steps) {
         // A step only has a row once it has started; `step/start` is what supplies this.
@@ -1275,7 +1263,7 @@ window.__ModuleLoader__.load({
         if (!statsStepHasFigures(entry.metrics)) continue
         const row = readingOfStatsStep(entry)
         // Attribute the request to the model that served it, for the speed column's tooltip.
-        const owner = models.get(row.key)
+        const owner = models === undefined ? undefined : models.get(row.key)
         if (owner !== undefined) {
           row.model = owner.model
           row.provider = owner.provider
@@ -2969,8 +2957,11 @@ window.__ModuleLoader__.load({
        * what made the drawer lag the log.
        */
       const statsRows = useMemo(
-        () => (sessionStats === undefined ? undefined : historyFromStats(sessionStats)),
-        [sessionStats],
+        () =>
+          sessionStats === undefined
+            ? undefined
+            : historyFromStats(sessionStats, modelIndexFromTrajectory(trajectory)),
+        [sessionStats, trajectory],
       )
       /*
        * Fallback for a composition without the statistics target: derive rows from the Chat

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-recent-usage-metrics",
-  "version": "0.3.0",
+  "version": "0.3.2",
   "description": "Geek level for the Performance & usage setting: a live reading of the newest request (first-token latency, speed, tokens, total, amortised) plus a drawer listing the last ten, all derived from the shipped Statistics view data",
   "repository": {
     "type": "git",