agent-inspect 6.31.17 → 6.31.19

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## 6.31.19
+
+### Patch Changes
+
+- 8df3096: Fix residual recovery attemptNumber undercount and invalid result-availability times; promote OTLP agent_inspect.\* identity into workflow metadata on read; harden packed MCP SDK e2e (429/cancel/overlap/readiness); complete keyless Fix-Owes fixture corpus (Om through Thorin, Bezalel invariants).
+
+## 6.31.18
+
+### Patch Changes
+
+- c65817e: Fix recovery result-availability ordering and mixed attemptId counting; emit bounded OTLP operation/attempt identity without broad attribute dump; add real MCP SDK packed e2e and Fix-Owes recipe corpus (variable paths, timeout ledger, access disclosure, browser observed outcomes, NestJS tenant, causal failure, headsign, Keniel B8).
+
 ## 6.31.17
 
 ### Patch Changes

package/README.md

@@ -213,7 +213,7 @@ The root package is enough for custom capture, the CLI, checks, and Evidence wor
 
 ## Status and documentation
 
-**Current published baseline:** **6.31.17** · persisted schema `1.0` · Node.js `>=20` · MIT.
+**Current published baseline:** **6.31.19** · persisted schema `1.0` · Node.js `>=20` · MIT.
 
 Legacy v0.1 and v0.2 traces remain readable. Check the npm badge and [changelog](CHANGELOG.md) for the current published version.
 

package/docs/COMPARE.md

@@ -106,7 +106,7 @@ OrcaReplay is a local CLI that records an agent run at the model-provider bounda
 
 AgentInspect is local-first CLI debugging:
 
-- Use AgentInspect to inspect and gate a run's trajectory; the two capture at different layers, so a run can be captured by both at once — AgentInspect instruments inside the process and produces an execution tree, while OrcaReplay proxies the provider connection and records the bytes on the wire.
+- Use AgentInspect to inspect and gate a run's trajectory; the two capture at different layers. AgentInspect builds a local execution tree from in-process instrumentation and from existing log/trace readers; OrcaReplay proxies the provider connection and records the bytes on the wire. Simultaneous AgentInspect + OrcaReplay capture on one run is possible in principle but **untested** here until a retained joint experiment exists.
 - If you reach for OrcaReplay, two limits are worth knowing: a matching replay is not a determinism result, and replay blocks model-provider egress only — it is not a sandbox, so recorded tool calls still execute and a tool that opens its own connection still reaches the network.
 - AgentInspect does not replay a recorded run; the README lists "a replay engine" among the things it is not.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-inspect",
-  "version": "6.31.17",
+  "version": "6.31.19",
   "license": "MIT",
   "type": "module",
   "description": "Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP",
@@ -236,7 +236,7 @@
     "test:all": "pnpm run typecheck && pnpm run linked-versions:check && pnpm run build && pnpm run test && pnpm run size",
     "prepublish:checks": "pnpm run typecheck && pnpm run build && pnpm run test && pnpm run test:coverage && pnpm run fixtures:check && pnpm run recipes:check && pnpm run test:integration-offline && pnpm run size && pnpm run linked-versions:check && pnpm run repo:health && pnpm run pack:smoke",
     "pack:dry-run": "pnpm run build && npm pack --dry-run",
-    "pack:smoke": "pnpm run package-licenses:check && pnpm run build && node scripts/package-smoke.mjs && node scripts/packed-openai-agents-e2e.mjs && node scripts/packed-ai-sdk-e2e.mjs && node scripts/packed-mcp-e2e.mjs && node scripts/packed-quickstart-e2e.mjs && node scripts/packed-semantic-loop-e2e.mjs && node scripts/packed-swarm-loop-e2e.mjs && node scripts/evidence-ci-golden-paths.mjs",
+    "pack:smoke": "pnpm run package-licenses:check && pnpm run build && node scripts/package-smoke.mjs && node scripts/packed-openai-agents-e2e.mjs && node scripts/packed-ai-sdk-e2e.mjs && node scripts/packed-mcp-e2e.mjs && node scripts/packed-mcp-sdk-e2e.mjs && node scripts/packed-quickstart-e2e.mjs && node scripts/packed-semantic-loop-e2e.mjs && node scripts/packed-swarm-loop-e2e.mjs && node scripts/evidence-ci-golden-paths.mjs",
     "linked-versions:check": "node scripts/check-linked-versions.mjs",
     "docs:commands": "node scripts/validate-doc-commands.mjs",
     "docs:links": "node scripts/validate-doc-links.mjs",

package/packages/cli/dist/{chunk-USZJEEME.mjs → chunk-NALE36AJ.mjs}

@@ -3696,7 +3696,7 @@ function extractSessionWorkflowMetadata(record) {
   assignString("conversationId", record.conversationId);
   assignString("groupId", record.groupId);
   assignString("parentGroupId", record.parentGroupId);
-  assignString("retryOf", record.retryOf);
+  assignString("retryOf", record.retryOf ?? record["agent_inspect.retry_of"]);
   assignString("retryReason", record.retryReason);
   assignString("handoffFrom", record.handoffFrom);
   assignString("handoffTo", record.handoffTo);
@@ -3709,8 +3709,8 @@ function extractSessionWorkflowMetadata(record) {
   assignString("toolCallId", record.toolCallId);
   assignString("mcpToolCallId", record.mcpToolCallId);
   assignString("linkedStepId", record.linkedStepId);
-  assignString("operationId", record.operationId);
-  assignString("attemptId", record.attemptId);
+  assignString("operationId", record.operationId ?? record["agent_inspect.operation_id"]);
+  assignString("attemptId", record.attemptId ?? record["agent_inspect.attempt_id"]);
   assignString("fallbackOf", record.fallbackOf);
   assignString("idempotencyKey", record.idempotencyKey);
   assignString("correlationId", record.correlationId);
@@ -3721,7 +3721,9 @@ function extractSessionWorkflowMetadata(record) {
     out.attempt = attempt;
     found = true;
   }
-  const attemptNumber = finitePositiveInt(record.attemptNumber);
+  const attemptNumber = finitePositiveInt(
+    record.attemptNumber ?? record["agent_inspect.attempt_number"]
+  );
   if (attemptNumber !== void 0) {
     out.attemptNumber = attemptNumber;
     found = true;
@@ -5737,24 +5739,35 @@ function attemptIdOf(event) {
   return typeof value === "string" && value.trim() !== "" ? value : void 0;
 }
 function countOperationAttempts(members) {
-  const attemptIds = new Set(
-    members.map((event) => attemptIdOf(event)).filter((value) => value !== void 0)
-  );
-  if (attemptIds.size > 0) {
-    return attemptIds.size;
+  const identified = /* @__PURE__ */ new Set();
+  let unidentified = 0;
+  for (const event of members) {
+    if (event.kind !== "TOOL" && event.kind !== "LLM") continue;
+    const id = attemptIdOf(event);
+    if (id !== void 0) {
+      identified.add(id);
+      continue;
+    }
+    unidentified += 1;
+  }
+  if (identified.size > 0) {
+    return identified.size + unidentified;
   }
-  const numbers = members.map((event) => attemptNumberOf(event)).filter((value) => value !== void 0).sort((a, b) => a - b);
-  if (numbers.length > 0) {
-    const unique = [...new Set(numbers)];
-    const min = unique[0];
-    const max = unique[unique.length - 1];
-    const contiguous = unique.length === max - min + 1 && unique.every((value, index) => value === min + index);
-    if (contiguous) {
-      return unique.length;
+  const numbered = /* @__PURE__ */ new Set();
+  let unnumbered = 0;
+  for (const event of members) {
+    if (event.kind !== "TOOL" && event.kind !== "LLM") continue;
+    const num = attemptNumberOf(event);
+    if (num !== void 0) {
+      numbered.add(num);
+      continue;
     }
-    return unique.length;
+    unnumbered += 1;
+  }
+  if (numbered.size > 0) {
+    return numbered.size + unnumbered;
   }
-  return members.filter((event) => event.kind === "TOOL" || event.kind === "LLM").length;
+  return unnumbered;
 }
 function classifyRetryAttempt(event, priorOrdered, allMembers) {
   const workflow = workflowFor(event);
@@ -6029,8 +6042,42 @@ function eventEvidence2(event) {
 function eventTime2(event) {
   return event.startedAt ?? event.timestamp ?? "";
 }
+function parseComparableMs(value) {
+  if (!value) return void 0;
+  const parsed = Date.parse(value);
+  return Number.isFinite(parsed) ? parsed : void 0;
+}
+function consumerStartMs(event) {
+  return parseComparableMs(event.startedAt) ?? parseComparableMs(event.timestamp);
+}
+function resultAvailableMs(event) {
+  const started = parseComparableMs(event.startedAt) ?? parseComparableMs(event.timestamp);
+  const endedRaw = event.endedAt;
+  const endedPresent = endedRaw !== void 0 && endedRaw !== null && String(endedRaw).trim() !== "";
+  if (endedPresent) {
+    const ended = parseComparableMs(typeof endedRaw === "string" ? endedRaw : String(endedRaw));
+    if (ended === void 0) return void 0;
+    if (started !== void 0 && ended < started) return void 0;
+    return ended;
+  }
+  if (event.durationMs !== void 0) {
+    if (!Number.isFinite(event.durationMs) || event.durationMs < 0) {
+      return void 0;
+    }
+    if (started !== void 0) {
+      return started + event.durationMs;
+    }
+    return void 0;
+  }
+  return parseComparableMs(event.timestamp);
+}
 function sortByTime2(events) {
-  return [...events].sort((a, b) => eventTime2(a).localeCompare(eventTime2(b)));
+  return [...events].sort((a, b) => {
+    const aMs = consumerStartMs(a) ?? 0;
+    const bMs = consumerStartMs(b) ?? 0;
+    if (aMs !== bMs) return aMs - bMs;
+    return eventTime2(a).localeCompare(eventTime2(b));
+  });
 }
 function errorCodeOf(event) {
   if (typeof event.error?.code === "string" && event.error.code.trim() !== "") {
@@ -6098,13 +6145,20 @@ function sameArguments(left, right) {
   }
   return { ok: true };
 }
+var UNEVALUABLE_WRITE_ERROR_CODES = /* @__PURE__ */ new Set([
+  "TIMEOUT",
+  "ETIMEDOUT",
+  "UNKNOWN_COMPLETION",
+  "DEADLINE_EXCEEDED"
+]);
 function isUnevaluableWriteCompletion(event) {
   if (event.status === "running" || event.status === "unknown") return true;
   const attrs = event.attributes ?? {};
   if (attrs.timeout === true) return true;
+  if (attrs.unknownCompletion === true) return true;
   if (attrs.completionState === "unknown" || attrs.completionState === "timeout") return true;
   const code = errorCodeOf(event)?.toUpperCase();
-  if (code === "TIMEOUT" || code === "UNKNOWN_COMPLETION" || code === "DEADLINE_EXCEEDED") {
+  if (code && UNEVALUABLE_WRITE_ERROR_CODES.has(code)) {
     return true;
   }
   return false;
@@ -6152,14 +6206,17 @@ function collectExplicitReferences(event) {
   return refs;
 }
 function llmReferencesTool(llm, toolEvent, requireExplicit) {
-  if (!requireExplicit) {
-    return eventTime2(llm) >= eventTime2(toolEvent);
-  }
-  const refs = collectExplicitReferences(llm);
-  if (refs.has(toolEvent.eventId)) return true;
-  const toolCallId = workflowFor2(toolEvent).toolCallId;
-  if (toolCallId && refs.has(toolCallId)) return true;
-  return false;
+  if (llm.runId !== toolEvent.runId) return false;
+  if (requireExplicit) {
+    const refs = collectExplicitReferences(llm);
+    const toolCallId = workflowFor2(toolEvent).toolCallId;
+    const hasRef = refs.has(toolEvent.eventId) || toolCallId !== void 0 && refs.has(toolCallId);
+    if (!hasRef) return false;
+  }
+  const resultMs = resultAvailableMs(toolEvent);
+  const consumerMs = consumerStartMs(llm);
+  if (resultMs === void 0 || consumerMs === void 0) return false;
+  return resultMs <= consumerMs;
 }
 function attemptIdOf2(event) {
   const value = workflowFor2(event).attemptId;
@@ -13573,6 +13630,70 @@ function mapOtlpEvents(value, pathPrefix) {
     unsupportedFields
   };
 }
+function promoteAgentInspectWorkflowIdentity(attributes, pathPrefix) {
+  const warnings = [];
+  const mapping = [
+    ["agent_inspect.operation_id", "operationId", "string"],
+    ["agent_inspect.attempt_id", "attemptId", "string"],
+    ["agent_inspect.retry_of", "retryOf", "string"],
+    ["agent_inspect.attempt_number", "attemptNumber", "int"]
+  ];
+  const metadata = attributes.metadata && typeof attributes.metadata === "object" && !Array.isArray(attributes.metadata) ? { ...attributes.metadata } : {};
+  for (const [dotted, camel, kind] of mapping) {
+    const raw = attributes[dotted];
+    if (raw === void 0 || raw === null) continue;
+    let promoted;
+    if (kind === "int") {
+      const n = typeof raw === "number" ? raw : typeof raw === "string" ? Number(raw) : NaN;
+      if (!Number.isFinite(n) || n < 1) {
+        warnings.push({
+          code: "otlp_identity_invalid",
+          message: `Ignoring invalid ${dotted} identity value.`,
+          severity: "warning",
+          field: `${pathPrefix}.${dotted}`
+        });
+        continue;
+      }
+      promoted = Math.trunc(n);
+    } else if (typeof raw === "string" && raw.trim() !== "") {
+      promoted = raw.trim();
+    } else {
+      warnings.push({
+        code: "otlp_identity_invalid",
+        message: `Ignoring non-string ${dotted} identity value.`,
+        severity: "warning",
+        field: `${pathPrefix}.${dotted}`
+      });
+      continue;
+    }
+    const direct = attributes[camel];
+    const nested = metadata[camel];
+    if (direct !== void 0 && direct !== promoted) {
+      warnings.push({
+        code: "otlp_identity_conflict",
+        message: `Conflicting ${camel}: attributes.${camel} vs ${dotted}; keeping camelCase.`,
+        severity: "warning",
+        field: `${pathPrefix}.${dotted}`
+      });
+      continue;
+    }
+    if (nested !== void 0 && nested !== promoted && direct === void 0) {
+      warnings.push({
+        code: "otlp_identity_conflict",
+        message: `Conflicting ${camel}: attributes.metadata.${camel} vs ${dotted}; keeping nested.`,
+        severity: "warning",
+        field: `${pathPrefix}.${dotted}`
+      });
+      continue;
+    }
+    if (direct === void 0) attributes[camel] = promoted;
+    if (nested === void 0) metadata[camel] = promoted;
+  }
+  if (Object.keys(metadata).length > 0) {
+    attributes.metadata = metadata;
+  }
+  return warnings;
+}
 function mapOtlpSpan(context) {
   const { span, pathPrefix } = context;
   const warnings = [];
@@ -13604,6 +13725,7 @@ function mapOtlpSpan(context) {
   if (context.scopeVersion !== void 0) {
     attributes["scope.version"] = context.scopeVersion;
   }
+  warnings.push(...promoteAgentInspectWorkflowIdentity(attributes, pathPrefix));
   for (const [key, value] of Object.entries(span)) {
     if (OTLP_SPAN_KEYS.has(key)) continue;
     unsupportedFields.push(`${pathPrefix}.${key}`);
@@ -13641,6 +13763,7 @@ function mapOtlpSpan(context) {
   if (events.events !== void 0) {
     attributes["otlp.events"] = events.events;
   }
+  warnings.push(...promoteAgentInspectWorkflowIdentity(attributes, pathPrefix));
   const traceId = readStringField(span, ["traceId"]) ?? "trace-unknown";
   const spanId = readStringField(span, ["spanId"]) ?? "span-unknown";
   const parentSpanId = readStringField(span, ["parentSpanId"]);
@@ -15547,5 +15670,5 @@ function renderGateReport(result, options = {}) {
 }
 
 export { ATTRIBUTION_CONFIDENCES, COHORT_METRIC_IDS, DEFAULT_REDACT_KEYS, DEFAULT_SUITE_ARTIFACTS_DIR, EVIDENCE_FORMAT_VERSION, EVIDENCE_HTML_FILENAME, EVIDENCE_MANIFEST_FILENAME, Redactor, TraceDirectory, TraceReadError, TreeBuilder, aggregateBundleSafeStatus, aggregateSessionCheckResults, analyzeCohort, applyProfileMetadataCaps, assertBundlePathContained, assertEvidenceRelativePath, buildActivitySummary, buildBundleMetadata, buildBundleSummaryMarkdown, buildEvidenceCausalFailureViewHtml, buildEvidenceCiPackage, buildEvidenceCircuitViewHtml, buildEvidenceContractsViewHtml, buildEvidenceDiffViewHtml, buildEvidenceHtmlShell, buildEvidenceManifest, buildEvidenceOutcomesViewHtml, buildEvidenceProvenanceViewHtml, buildEvidenceSafetyViewHtml, buildEvidenceTimelineViewHtml, buildEvidenceToolsLlmViewHtml, buildEvidenceTreeViewHtml, buildLocalExplanation, buildPlaceholderArtifact, buildRunSummary, buildRunTimeline, buildRunWhatSummary, buildSessionIndex, buildTraceStats, buildZipArchive, bundleFailsOnSafety, bundleRunAssetRelativePath, collectTraceSchemaVersions, compactAttributes, createBaselineRegressionRule, createLlmUsageRule, createMaxStepDurationRule, createObservedOutcomeRule, createRequireCompletedRule, createRunDepthRule, createRunDurationRule, createRunStatusRule, createSafetyOversizedAttributeRule, createSafetyRawContentRule, createSafetyRedactionRule, createSafetySecretPatternRule, createStallDetectionRule, createStructureCycleRule, createStructureOrphanRule, createStructureParallelWidthRule, createStructureRelationshipRule, createToolUsageRule, defaultBundleOutputPath, defaultSuiteConfigTemplate, defineTraceContract, diffRuns, diffTraceEvents, enrichSessionRunRecord, escapeHtml, escapeMarkdown, evaluateTraceContract, extractMetadata, extractOutcomesFromTraceEvents, filterMetasBySessionScope, filterTraces, flattenTree, formatDuration2 as formatDuration, formatStepLabel, formatTimestamp, gateHasThresholds, getIndent, getTraceFilePath, inferEvidenceFileRole, isAgentInspectTrace, isAttributionConfidence, isCredentialSensitiveKey, isPersistedInspectEvent, loadSessionRunRecords, loadSuiteConfig, loadTraceMetadataList, manualTraceEventsToComparableRun, nanoid, normalizeBundleOutputPath, openTrace, parseCohortMetricList, parseDuration, parseDurationFilter, parseGateList, parseTraceJsonl, persistedInspectEventsToRunTrees, persistedInspectEventsToTraceEvents, projectLogicalEvents, renderActivitySummaryHuman, renderCohortReport, renderErrorLine, renderGateReport, renderObservedOutcomesHtml, renderObservedOutcomesMarkdown, renderRunDiff, renderRunWhat, renderStepLine, renderSuiteReport, renderTimeline, renderTraceStats, resolveBundleRunIds, resolveRedactionProfile, resolveSuiteTemplate, resolveTraceDir, runGate, runSuite, runTraceChecks, safeString, sanitizeBundleRunId, searchTraces, serializeEvidenceManifest, sha256Hex, stableJson, stringContainsHighConfidenceCredential, summarizeObservedOutcomes, summarizeSemanticParity, traceEventToPersistedInspectEvent, truncateName, truncateStringForProfile, validateEvent, validateSuiteConfig, verifyEvidenceDirectory, zeroKinds };
-//# sourceMappingURL=chunk-USZJEEME.mjs.map
-//# sourceMappingURL=chunk-USZJEEME.mjs.map
+//# sourceMappingURL=chunk-NALE36AJ.mjs.map
+//# sourceMappingURL=chunk-NALE36AJ.mjs.map