@leostera/evalkit 0.6.0 → 0.6.1

package/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 All notable changes to `@leostera/evalkit`. The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and the project uses [Semantic Versioning](https://semver.org/). Before 1.0, a minor version may include breaking changes; they are marked **Breaking**.
 
+## [0.6.1] - 2026-10-30
+
+Readable trajectories on the trial page.
+
+### Added
+
+- **Readable trajectories.** The trial page shows the trajectory as a conversation grouped by turn: the user's message, tool calls paired with their results (arguments and results expand), replies as text, and each checkpoint as one verdict with its duration. Lifecycle events are folded away; **All events** lists every raw event, each expandable to its JSON. Turns show latency and token usage when the agent reports them.
+- The runner records each user step's message on its `transcript-step-started` event (`message`), so trajectories include what the agent was asked.
+
 ## [0.6.0] - 2026-10-30
 
 Scenarios, datasets and CI reporting ([RFD0007](docs/rfds/RFD0007-scenarios-datasets-and-ci-reporting.md)). This release has breaking changes; see [Migrating from 0.5](#migrating-from-05) below.
@@ -138,10 +147,11 @@ Commit provenance and team sharing ([RFD0006](docs/rfds/RFD0006-commit-provenanc
 - **Breaking:** the npm package moved to `@leostera/evalkit`. Replace the `@leostera-js/evalkit` dependency and update imports, including `/runner`. Eval definitions and local reports are unchanged.
 - Dashboard workflow refinements.
 
-[0.6.0]: https://github.com/leostera/evalkit/compare/72148d4...main
-[0.5.0]: https://github.com/leostera/evalkit/compare/0dd8717...72148d4
-[0.4.0]: https://github.com/leostera/evalkit/compare/5e67e72...0dd8717
-[0.3.0]: https://github.com/leostera/evalkit/compare/38c34be...5e67e72
-[0.2.0]: https://github.com/leostera/evalkit/compare/3f8855a...38c34be
-[0.1.0]: https://github.com/leostera/evalkit/compare/12d5a1e...3f8855a
-[0.0.2]: https://github.com/leostera/evalkit/compare/0016e72...12d5a1e
+[0.6.1]: https://github.com/leostera/evalkit/compare/91c2c86...main
+[0.6.0]: https://github.com/leostera/evalkit/compare/99008d5...91c2c86
+[0.5.0]: https://github.com/leostera/evalkit/compare/49ad689...99008d5
+[0.4.0]: https://github.com/leostera/evalkit/compare/175bfcd...49ad689
+[0.3.0]: https://github.com/leostera/evalkit/compare/d45b221...175bfcd
+[0.2.0]: https://github.com/leostera/evalkit/compare/49471c3...d45b221
+[0.1.0]: https://github.com/leostera/evalkit/compare/b03233b...49471c3
+[0.0.2]: https://github.com/leostera/evalkit/compare/f13f20b...b03233b

package/dist/cli.mjs

@@ -1,7 +1,7 @@
 #!/bin/sh
 ':' //; exec "${EVALKIT_RUNTIME:-$(command -v bun || command -v node)}" "$0" "$@"
-import { L as defineEvalMatrix, R as canonicalParameters, d as recordError, f as registerEvals, i as authoringId, r as agentRuntimes, s as defineSuite } from "./src-D4tCwxNb.mjs";
-import { a as readRunSummary, d as staticDatasetFile, f as staticDatasetFiles, i as readRunManifest, l as readTrialSummary, n as runMatrix, o as readTrialEvents, r as ownerIsGone, s as readTrialManifest, t as runEval, u as localReportStore } from "./src-CVSCn3bZ.mjs";
+import { L as defineEvalMatrix, R as canonicalParameters, d as recordError, f as registerEvals, i as authoringId, r as agentRuntimes, s as defineSuite } from "./src-CZPufWN_.mjs";
+import { a as readRunSummary, d as staticDatasetFile, f as staticDatasetFiles, i as readRunManifest, l as readTrialSummary, n as runMatrix, o as readTrialEvents, r as ownerIsGone, s as readTrialManifest, t as runEval, u as localReportStore } from "./src-CKqOzeBi.mjs";
 import { c as dashboardIndex, d as encodeBundle, o as repoKey } from "./index-db-vbqEGFaU.mjs";
 import { t as createDirectoryShareApp } from "./src-CZnDXP1K.mjs";
 import * as Schema from "effect/Schema";
@@ -9294,7 +9294,7 @@ function allSkipped(scenario) {
 //#endregion
 //#region ../cli/src/version.ts
 /** The CLI version; kept in sync with package.json when releasing. */
-const VERSION = "0.6.0";
+const VERSION = "0.6.1";
 //#endregion
 //#region ../cli/src/run-command.ts
 function parseRunArgs(args) {
@@ -9922,7 +9922,7 @@ scores, evidence, and candidate files (never evaluator workspaces): review it be
 }
 //#endregion
 //#region ../cli/src/new-project.ts
-const npmDependency = "^0.6.0";
+const npmDependency = "^0.6.1";
 const ignored = [
 	"node_modules/",
 	"_evalkit-results/",