codex-copilot-dx 0.9.4 → 0.9.5

package/README.md

@@ -107,7 +107,7 @@ This performs a fresh, read-only GitHub Copilot model-directory lookup without s
 
 Interactive terminals use aligned tables for `models`, `auth status`, and `usage`. Redirected or piped output retains the plain-text layout for scripts; use `--format table` or `--format plain` when a command offers an explicit format override.
 
-`ccdx usage` and the dashboard Usage table show token cache hit rate for each model and the aggregate: cached input tokens divided by input tokens, weighted by token count rather than averaging request percentages. This describes the upstream prompt cache; the local history and image-transform caches are separate. A rate is `—` when input tokens are zero or any included record lacks valid paired input/cache counts. Older logs may omit explicit zero cache counts; new Responses usage records retain reported zeros. CLI tables keep existing token columns on narrow terminals and show rates below the table when the extra column does not fit.
+`ccdx usage` and the dashboard Usage table show token cache hit rate for each model and the aggregate: recorded cached input tokens divided by recorded input tokens, weighted by token count rather than averaging request percentages. This describes the upstream prompt cache; the local history and image-transform caches are separate. Incomplete historical records do not hide a computable ratio: `~` marks a rate derived from incomplete counts. A rate is `—` when input tokens are zero, usable totals are missing, or token counts are invalid. Older logs may omit explicit zero cache counts; new Responses usage records retain reported zeros. CLI tables keep existing token columns on narrow terminals and show rates below the table when the extra column does not fit.
 
 ### Auto-review model
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "codex-copilot-dx",
-  "version": "0.9.4",
+  "version": "0.9.5",
   "description": "Use Codex App with GitHub Copilot",
   "author": "Dale Xiao",
   "type": "module",

package/src/dashboard/index.html

@@ -64,7 +64,7 @@
           <div class="panel-heading"><h2>USAGE</h2><div class="heading-actions"><span id="usage-state">READING LOG</span><button id="refresh-usage" type="button">Refresh</button></div></div>
           <p id="usage-note" class="table-note">Aggregating local usage metadata…</p>
           <div class="table-wrap"><table class="usage-table"><thead><tr><th scope="col">MODEL</th><th scope="col">CALLS</th><th scope="col">INPUT</th><th scope="col">CACHE READ</th><th scope="col">OUTPUT</th><th scope="col">TOTAL</th><th scope="col">CACHE HIT</th></tr></thead><tbody id="usage-body"><tr><td colspan="7">Loading…</td></tr></tbody></table></div>
-          <p class="hint">Cache hit = cached / input tokens. — = incomplete usage data or no input tokens.</p>
+          <p class="hint">Cache hit = recorded cached / input tokens. ~ = incomplete history. — = unavailable or invalid counts.</p>
         </section>
 
         <section class="lower" aria-label="Recent failures">

package/src/dashboard/ui.js

@@ -309,7 +309,7 @@ async function loadModels() {
 
 function usageValues(row) {
   const rate = Number.isFinite(row.cache_hit_rate) && row.cache_hit_rate >= 0 && row.cache_hit_rate <= 1
-    ? `${(row.cache_hit_rate * 100).toFixed(1)}%` : "—";
+    ? `${row.cache_hit_rate_partial ? "~" : ""}${(row.cache_hit_rate * 100).toFixed(1)}%` : "—";
   return [row.model, number(row.requests), number(row.input_tokens), number(row.cache_read_tokens), number(row.output_tokens), number(row.total_tokens), rate];
 }
 

package/src/dashboard-api.mjs

@@ -86,6 +86,7 @@ function usageRow(model, values) {
     input_tokens: finite(values.input_tokens),
     cache_read_tokens: cacheReadTokens(values) ?? null,
     cache_hit_rate: usageCacheHitRate(values),
+    cache_hit_rate_partial: values.cache_hit_unknown_requests > 0,
     output_tokens: finite(values.output_tokens),
     total_tokens: finite(values.total_tokens),
   };

package/src/usage.mjs

@@ -277,6 +277,13 @@ export function summarizeUsage(records) {
       summary.totals.cache_hit_unknown_requests = (summary.totals.cache_hit_unknown_requests || 0) + 1;
       modelTotals.cache_hit_unknown_requests = (modelTotals.cache_hit_unknown_requests || 0) + 1;
     }
+    const cacheCounts = [record.usage?.cached_input_tokens, record.usage?.cache_read_input_tokens];
+    if ((input != null && (!Number.isFinite(input) || input < 0))
+      || cacheCounts.some((value) => value != null && (!Number.isFinite(value) || value < 0))
+      || (Number.isFinite(input) && Number.isFinite(cached) && cached > input)) {
+      summary.totals.cache_hit_invalid_requests = (summary.totals.cache_hit_invalid_requests || 0) + 1;
+      modelTotals.cache_hit_invalid_requests = (modelTotals.cache_hit_invalid_requests || 0) + 1;
+    }
   }
   return summary;
 }
@@ -315,14 +322,14 @@ export function cacheReadTokens(usage = {}) {
 export function usageCacheHitRate(usage = {}) {
   const input = usage.input_tokens;
   const cached = cacheReadTokens(usage);
-  if (usage.cache_hit_unknown_requests > 0 || !Number.isFinite(input) || input <= 0
+  if (usage.cache_hit_invalid_requests > 0 || !Number.isFinite(input) || input <= 0
     || !Number.isFinite(cached) || cached < 0 || cached > input) return null;
   return cached / input;
 }
 
 function cacheHitPercent(usage) {
   const rate = usageCacheHitRate(usage);
-  return rate === null ? "—" : `${(rate * 100).toFixed(1)}%`;
+  return rate === null ? "—" : `${usage.cache_hit_unknown_requests > 0 ? "~" : ""}${(rate * 100).toFixed(1)}%`;
 }
 
 function formatPlainUsageSummary(summary, filePath, { sanitize = false } = {}) {