agent-inspect 6.7.2 → 6.7.3

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## 6.7.3
+
+### Patch Changes
+
+- ac6747d: Corrective patch after 6.7.2: TraceContract allowed-status handling, OpenInference nano timestamp strings, cohort maxRelativeDelta for all numeric metrics, Windows path portability, CLI search --session exit codes, diff/normalizer correctness, Studio auth timing / ingest / bundle dedup, and related test hardening. No schema break; no new product surface.
+
 ## Unreleased
 
 ## 6.7.2

package/README.md

@@ -131,7 +131,7 @@ Details: [Safe sharing](https://github.com/rajudandigam/agent-inspect/blob/main/
 
 ## Project status
 
-**Current release:** **6.7.2** (eighteen linked npm packages). Technical launch candidate; external pilot evidence pending. Persisted schema **1.0**. Node.js **≥ 20**. **v7 not scheduled.**
+**Current release:** **6.7.3** (eighteen linked npm packages). Technical launch candidate; external pilot evidence pending. Persisted schema **1.0**. Node.js **≥ 20**. **v7 not scheduled.**
 
 [Roadmap](ROADMAP.md) · [Pilot kit](https://github.com/rajudandigam/agent-inspect/blob/main/docs/PRE-V7-PILOT-KIT.md) · [Changelog](CHANGELOG.md)
 

package/docs/EXPORTS.md

@@ -36,6 +36,14 @@ agent-inspect export minimal-success --dir fixtures/traces --format markdown
 - **HTML:** export writes a local file; a rendered-report visual is pending re-record ([RECORDING.md](./assets/demos/RECORDING.md)). Use `agent-inspect export <run-id> --format html -o report.html` and open the file locally.
 - **OpenInference / OTLP JSON:** compatibility-oriented shapes for local handoff — validate with `--validate` before sharing. No dedicated GIF; see format tables below.
 
+### Fixture-backed export evidence
+
+The canonical OpenInference export of a persisted schema **1.0** trace is committed at
+[`fixtures/standards/openinference-export-golden.json`](../fixtures/standards/openinference-export-golden.json)
+(generated from `fixtures/traces-v1.0/manual-basic.jsonl`; regeneration is asserted byte-stable in
+`packages/core/test/exporters/openinference-export-golden.test.ts`). Nanosecond timestamps are decimal strings,
+matching the import fixtures and the OTLP exporter.
+
 ## Common options
 
 | Flag | Notes |
@@ -90,6 +98,7 @@ Prefer the smallest useful artifact — a summary or synthetic reproduction beat
 
 ## Related docs
 
+- [STANDARDS-GRADUATION.md](./STANDARDS-GRADUATION.md) — export → review → optional import path
 - [CLI.md](./CLI.md) — `export` command reference
 - [SCHEMA.md](./SCHEMA.md) — trace event model and redaction notes
 - [SAFE-TRACE-SHARING.md](./SAFE-TRACE-SHARING.md) — checklist before posting

package/docs/PERFORMANCE.md

@@ -12,6 +12,24 @@ pnpm perf:baseline
 
 The script prints deterministic timings for parse, normalize, tree build, diff, export, and checks on synthetic data. Warnings appear when a step exceeds internal soft thresholds.
 
+## Performance fixtures
+
+[`fixtures/performance/`](../fixtures/performance/README.md) ships three deterministic size tiers with the same event shape as the baseline's synthetic traces, for exercising CLI paths against stable on-disk inputs:
+
+| File | Steps | Events |
+| ---- | ----- | ------ |
+| `perf-small.jsonl` | 10 | 22 |
+| `perf-medium.jsonl` | 100 | 202 |
+| `perf-large.jsonl` | 500 | 1,002 |
+
+```bash
+npx agent-inspect view perf-large --dir fixtures/performance
+npx agent-inspect report perf-large --dir fixtures/performance
+npx agent-inspect stats --dir fixtures/performance
+```
+
+All three are validated by `pnpm fixtures:check` and small enough for git (the largest is well under 1 MB).
+
 ## Comfortable ranges (v3.4)
 
 | Workload | Comfortable | Warning | Not designed for |

package/docs/STANDARDS.md

@@ -31,6 +31,10 @@ GenAI attribute mapping follows `OTEL_GEN_AI_SEMCONV_PIN` (see exporters API). N
 
 Fixture: [fixtures/standards/otlp-basic.json](../fixtures/standards/otlp-basic.json)
 
+## Graduation guide
+
+Full path from local export through review to optional customer-owned import: [STANDARDS-GRADUATION.md](./STANDARDS-GRADUATION.md).
+
 ## Import recipes
 
 - [Phoenix / OpenInference](../examples/recipes/phoenix-openinference-import/)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-inspect",
-  "version": "6.7.2",
+  "version": "6.7.3",
   "license": "MIT",
   "type": "module",
   "description": "Debug, regression-test, and safely share TypeScript AI-agent behavior locally — no account, no default upload, metadata-only by default",
@@ -216,7 +216,7 @@
     "vitest": "^2.1.8"
   },
   "scripts": {
-    "clean": "pnpm -r exec -- rm -rf dist",
+    "clean": "pnpm -r exec -- node -e \"require('node:fs').rmSync('dist',{recursive:true,force:true})\"",
     "build": "pnpm exec tsup --config tsup.core.config.ts && pnpm exec tsup --config tsup.cli.config.ts && pnpm exec tsup --config tsup.langchain.config.ts && pnpm exec tsup --config tsup.tui.config.ts && pnpm exec tsup --config tsup.ai-sdk.config.ts && pnpm exec tsup --config tsup.vitest.config.ts && pnpm exec tsup --config tsup.jest.config.ts && pnpm exec tsup --config tsup.openai-agents.config.ts && pnpm exec tsup --config tsup.harness.config.ts && pnpm exec tsup --config tsup.redact.config.ts && pnpm exec tsup --config tsup.eval.config.ts && pnpm exec tsup --config tsup.mcp.config.ts && pnpm exec tsup --config tsup.guardrails.config.ts && pnpm exec tsup --config tsup.circuit.config.ts && pnpm exec tsup --config tsup.viewer.config.ts && pnpm exec tsup --config tsup.mcp-server.config.ts && pnpm exec tsup --config tsup.adapter-sdk.config.ts && pnpm exec tsup --config tsup.vscode.config.ts && pnpm exec tsup --config tsup.index-sqlite.config.ts && pnpm exec tsup --config tsup.studio.config.ts",
     "typecheck": "tsc --noEmit",
     "test": "vitest run",

package/packages/cli/dist/{chunk-M6PC5KUT.mjs → chunk-EMYDJREA.mjs}

@@ -8137,7 +8137,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Average duration (ms)",
           baselineAgg?.avgDurationMs,
-          candidateAgg?.avgDurationMs
+          candidateAgg?.avgDurationMs,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8147,7 +8149,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Average LLM calls",
           baselineAgg?.avgLlmCallCount,
-          candidateAgg?.avgLlmCallCount
+          candidateAgg?.avgLlmCallCount,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8157,7 +8161,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Average token usage",
           baselineAgg?.avgTokenUsage,
-          candidateAgg?.avgTokenUsage
+          candidateAgg?.avgTokenUsage,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8167,7 +8173,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Average retries",
           baselineAgg?.avgRetryCount,
-          candidateAgg?.avgRetryCount
+          candidateAgg?.avgRetryCount,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8177,7 +8185,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Observation failure rate",
           baselineAgg?.observationFailureRate,
-          candidateAgg?.observationFailureRate
+          candidateAgg?.observationFailureRate,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8213,7 +8223,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Guardrail failures",
           baselineAgg?.avgGuardrailFailures,
-          candidateAgg?.avgGuardrailFailures
+          candidateAgg?.avgGuardrailFailures,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8223,7 +8235,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Circuit violations",
           baselineAgg?.avgCircuitViolations,
-          candidateAgg?.avgCircuitViolations
+          candidateAgg?.avgCircuitViolations,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -8233,7 +8247,9 @@ function compareCohortAggregates(groups, options) {
           metric,
           "Redaction warnings",
           baselineAgg?.avgRedactionWarnings,
-          candidateAgg?.avgRedactionWarnings
+          candidateAgg?.avgRedactionWarnings,
+          true,
+          tolerance
         );
         if (item) comparisons.push(item);
         break;
@@ -9045,5 +9061,5 @@ function renderGateReport(result, options = {}) {
 }
 
 export { COHORT_METRIC_IDS, DEFAULT_SUITE_ARTIFACTS_DIR, Redactor, TraceDirectory, TraceReadError, TreeBuilder, __commonJS, __require, __toESM, aggregateBundleSafeStatus, aggregateSessionCheckResults, analyzeCohort, applyProfileMetadataCaps, assertBundlePathContained, buildActivitySummary, buildBundleMetadata, buildBundleSummaryMarkdown, buildLocalExplanation, buildPlaceholderArtifact, buildRunSummary, buildRunTimeline, buildRunWhatSummary, buildSessionIndex, buildTraceStats, bundleFailsOnSafety, bundleRunAssetRelativePath, compactAttributes3 as compactAttributes, createBaselineRegressionRule, createLlmUsageRule, createMaxStepDurationRule, createObservedOutcomeRule, createRequireCompletedRule, createRunDepthRule, createRunDurationRule, createRunStatusRule, createSafetyOversizedAttributeRule, createSafetyRawContentRule, createSafetyRedactionRule, createSafetySecretPatternRule, createStallDetectionRule, createStructureCycleRule, createStructureOrphanRule, createStructureParallelWidthRule, createStructureRelationshipRule, createToolUsageRule, defaultBundleOutputPath, defaultSuiteConfigTemplate, enrichSessionRunRecord, escapeHtml, escapeMarkdown, extractMetadata, extractOutcomesFromTraceEvents, filterMetasBySessionScope, filterTraces, flattenTree, formatDuration2 as formatDuration, formatTimestamp, gateHasThresholds, getIndent, getTraceFilePath, isAgentInspectTrace, isPersistedInspectEvent, loadSessionRunRecords, loadSuiteConfig, loadTraceMetadataList, nanoid, normalizeBundleOutputPath, openTrace, parseCohortMetricList, parseDuration, parseDurationFilter, parseGateList, parseTraceJsonl, persistedInspectEventsToTraceEvents, renderActivitySummaryHuman, renderCohortReport, renderErrorLine, renderGateReport, renderObservedOutcomesHtml, renderObservedOutcomesMarkdown, renderRunWhat, renderStepLine, renderSuiteReport, renderTimeline, renderTraceStats, resolveBundleRunIds, resolveRedactionProfile, resolveSuiteTemplate, resolveTraceDir, runGate, runSuite, runTraceChecks, safeString, sanitizeBundleRunId, searchTraces, source_default, stableJson, summarizeObservedOutcomes, traceEventToPersistedInspectEvent, truncateName, truncateStringForProfile, validateEvent, validateSuiteConfig, zeroKinds };
-//# sourceMappingURL=chunk-M6PC5KUT.mjs.map
-//# sourceMappingURL=chunk-M6PC5KUT.mjs.map
+//# sourceMappingURL=chunk-EMYDJREA.mjs.map
+//# sourceMappingURL=chunk-EMYDJREA.mjs.map