@klars/agentobs 0.2.1 → 0.2.2

package/dist/adapters/claude-transcript.js

@@ -135,14 +135,19 @@ export async function importTranscript(db, file) {
         const message = (row.message ?? {});
         const usage = message.usage;
         if (usage && typeof usage === 'object') {
-            // Only genuinely fresh input tokens go in tokensIn. Cache writes and
-            // reads are tracked separately because they bill at different rates,
-            // and because a cache read replays the whole context every turn - the
-            // headline token count must not include the same tokens hundreds of
-            // times.
-            result.tokensIn += usage.input_tokens ?? 0;
+            // Fresh input = uncached input + cache writes. A cache write is real
+            // new content being sent for the first time (just stored for reuse), so
+            // excluding it made "tokens in" absurd: 24K in against 4.6M out, when
+            // real agent usage is heavily input-weighted. It is still tracked
+            // separately for costing, since it bills at 1.25x.
+            //
+            // Cache *reads* stay out of this total: they replay the entire context
+            // on every turn, so counting them would report the same tokens hundreds
+            // of times (2.4 billion across three sessions).
+            const cacheWrite = usage.cache_creation_input_tokens ?? 0;
+            result.tokensIn += (usage.input_tokens ?? 0) + cacheWrite;
             result.tokensOut += usage.output_tokens ?? 0;
-            result.cacheWriteTokens += usage.cache_creation_input_tokens ?? 0;
+            result.cacheWriteTokens += cacheWrite;
             // cache_read is the whole conversation context replayed on every single
             // message, so it re-counts the same tokens on each turn - summing it
             // reported 413 million tokens for one session. It is tracked separately
@@ -186,6 +191,8 @@ export async function importTranscript(db, file) {
     }
     if (!sessionStarted)
         return result;
+    // tokensIn already contains the cache-write tokens, so they are costed once
+    // at the base rate here and only topped up by the extra 0.25x premium.
     const baseCost = computeCost(result.model, result.tokensIn, result.tokensOut);
     const readCost = computeCost(result.model, result.cacheReadTokens, 0);
     const writeCost = computeCost(result.model, result.cacheWriteTokens, 0);
@@ -194,7 +201,7 @@ export async function importTranscript(db, file) {
             ? null
             : baseCost +
                 (readCost ?? 0) * CACHE_READ_RATE +
-                (writeCost ?? 0) * CACHE_WRITE_RATE;
+                (writeCost ?? 0) * (CACHE_WRITE_RATE - 1);
     // Session totals come from the transcript's own usage blocks, which are
     // authoritative - the per-call rows have no tokens to sum.
     db.prepare(`UPDATE sessions

package/dist/server/public/app.js

@@ -191,10 +191,10 @@ function renderTools(rows) {
   body.replaceChildren();
   if (rows.length === 0) {
     const tr = document.createElement('tr');
-    const msg =
-      state.summary && state.summary.coarse_sessions > 0
-        ? 'Coarse sessions record no tool calls — connect the Claude Code hook for per-tool detail.'
-        : 'No tool calls recorded yet.';
+    const msg =
+      state.summary && state.summary.coarse_sessions > 0
+        ? 'Coarse sessions record no tool calls — connect the Claude Code hook for per-tool detail.'
+        : 'No tool calls recorded yet.';
     tr.append(Object.assign(cell(msg, 'empty'), { colSpan: 5 }));
     body.append(tr);
     return;
@@ -630,6 +630,16 @@ function renderDelta(el, current, previous, { goodWhenUp = true } = {}) {
     return;
   }
   const change = ((current - previous) / previous) * 100;
+  // A tiny previous period produces a huge, meaningless percentage - "+2300%"
+  // says nothing except that yesterday was nearly empty. Cap the display so
+  // the chip stays informative rather than theatrical.
+  if (Math.abs(change) > 999) {
+    el.className = `delta ${change > 0 === goodWhenUp ? 'delta-good' : 'delta-bad'}`;
+    el.textContent = `${change > 0 ? '▲' : '▼'} vs ${previous}`;
+    el.title = `Previous period had only ${previous}; a percentage would be misleading`;
+    el.removeAttribute('hidden');
+    return;
+  }
   if (!Number.isFinite(change) || Math.abs(change) < 0.5) {
     // Below half a percent is noise; a chip there implies a signal that
     // isn't real.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@klars/agentobs",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "Observability and control layer for AI coding agents - see every tool call, token, and dollar your agents spend, and stop them before they do something risky.",
   "license": "MIT",
   "author": "Klars AI",