agent-inspect 6.31.35 → 6.31.36

package/packages/core/dist/advanced.mjs

@@ -1,5 +1,5 @@
-import { extractSessionWorkflowMetadata, sessionKeyForRun, defineTraceContract, runTraceChecks, createRunStatusRule, createToolUsageRule, createRunDurationRule, createRunDepthRule, createToolFailureRule, createLlmUsageRule, createObservedOutcomeRule } from './chunk-3OMB34E6.mjs';
-export { extractSessionWorkflowMetadata, sessionKeyForRun } from './chunk-3OMB34E6.mjs';
+import { extractSessionWorkflowMetadata, sessionKeyForRun, defineTraceContract, runTraceChecks, createRunStatusRule, createToolUsageRule, createRunDurationRule, createRunDepthRule, createToolFailureRule, createLlmUsageRule, createObservedOutcomeRule } from './chunk-KQX3Z4DH.mjs';
+export { extractSessionWorkflowMetadata, sessionKeyForRun } from './chunk-KQX3Z4DH.mjs';
 export { MAX_TERMINAL_DEPTH, MAX_TERMINAL_NAME_LENGTH, TERMINAL_INDENT, TraceDirectory, createInspector, createInspectorRuntime, formatTerminalName, getCurrentContext, getCurrentCorrelationMetadata, getCurrentDepth, getCurrentRunId, getCurrentRunName, getCurrentStepId, getIndent, getParentStepId, getTraceDirFromContext, getTraceSafetyFromContext, hasActiveContext, isAgentInspectEnabled, isSilentContext, maybeInspectRun, printError, printFailedAt, printRunComplete, printRunStart, printStepComplete, printStepStart, renderErrorLine, renderRunSummary, renderStepLine, resolveTraceDir, runWithContext, runWithStepContext } from './chunk-X5RP2E2H.mjs';
 import { buildRunTimeline, filterTraces, extractMetadata, buildRunSummary } from './chunk-2SKAI5ZN.mjs';
 export { buildRunSummary, buildRunTimeline, buildRunWhatSummary, buildTraceStats, extractMetadata, filterTraces, formatStepLabel, renderRunWhat, renderTimeline, renderTraceStats } from './chunk-2SKAI5ZN.mjs';

package/packages/core/dist/checks.cjs

@@ -5336,6 +5336,9 @@ function createToolFailureRule(options) {
     }
   };
 }
+function recordsTokenUsage(event) {
+  return Object.values(event.tokenUsage ?? {}).some((count) => typeof count === "number");
+}
 function createLlmUsageRule(options) {
   return {
     id: "llm.usage",
@@ -5393,6 +5396,21 @@ function createLlmUsageRule(options) {
         ["total", options.maxTotalTokens],
         ["cached", options.maxCachedTokens]
       ];
+      const hasTokenLimit = tokenLimits.some(([, limit]) => limit !== void 0);
+      const callsWithoutUsage = llms.filter(
+        (event) => event.status !== "error" && !recordsTokenUsage(event)
+      );
+      if (hasTokenLimit && callsWithoutUsage.length > 0) {
+        findings.push(
+          failFinding(
+            "llm.usage",
+            `No token usage was read for ${callsWithoutUsage.length} of ${llms.length} LLM call(s), so the token limit cannot be verified.`,
+            callsWithoutUsage.map((event) => eventEvidence3(event, "tokenUsage")),
+            "token usage on every completed LLM call",
+            { callsWithoutUsage: callsWithoutUsage.length, calls: llms.length }
+          )
+        );
+      }
       for (const [key, limit] of tokenLimits) {
         if (limit !== void 0 && tokenTotals[key] > limit) {
           findings.push(