From cea100cb01ee37f61f4ea4c4a6ce180dbf2adf9a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?David=20Hanu=C5=A1?= Date: Fri, 3 Jul 2026 00:44:43 +0200 Subject: [PATCH] fix(runner): restore simple 5-column dataset view + drop stale root schema MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The Console's dataset "Views" tab is driven by actors/runner/.actor/dataset_schema.json. The shape landed in b17cb10 (alongside judgeMode + OTel) tried to project every metric as a dot-path column and split verdicts into a second view. Nice telemetry, but the tab lost its "at-a-glance" property: overallVerdict got demoted from column 1 to column 5, testPrompt and agentOutput were dropped, and the second Verdicts view rendered each check as one opaque JSON blob. This PR replaces .views with a single Eval Results view — the five columns that answer "what happened on this test": Test # | Verdict | Prompt | Agent Output | Checks verdicts is rendered as an inline array (compact list of check objects) rather than a full unwound table. If someone needs per-check drill-down, the raw dataset item is still one click away in the Data tab; the Views tab optimizes for scanning. Also deletes the stale root-level .actor/dataset_schema.json — the pre-flatten copy that survived PR #13 and confused everyone about which file was live. Co-Authored-By: Claude Opus 4.7 --- .actor/dataset_schema.json | 88 --------------------- actors/runner/.actor/dataset_schema.json | 99 ++---------------------- 2 files changed, 8 insertions(+), 179 deletions(-) delete mode 100644 .actor/dataset_schema.json diff --git a/.actor/dataset_schema.json b/.actor/dataset_schema.json deleted file mode 100644 index 2705c68..0000000 --- a/.actor/dataset_schema.json +++ /dev/null @@ -1,88 +0,0 @@ -{ - "actorSpecification": 1, - "fields": {}, - "views": { - "results": { - "title": "Eval Results", - "transformation": { - "fields": [ - "overallVerdict", - "scenarioName", - "testIndex", - "agent", - "model", - "stopReason", - "testPrompt", - "agentOutput", - "verdicts", - "metrics", - "efficiency", - "trajectory", - "discoverability", - "error" - ] - }, - "display": { - "component": "table", - "properties": { - "overallVerdict": { - "label": "Verdict", - "format": "text" - }, - "scenarioName": { - "label": "Scenario", - "format": "text" - }, - "testIndex": { - "label": "Test #", - "format": "number" - }, - "agent": { - "label": "Agent", - "format": "text" - }, - "model": { - "label": "Model", - "format": "text" - }, - "stopReason": { - "label": "Stop Reason", - "format": "text" - }, - "testPrompt": { - "label": "Prompt", - "format": "text" - }, - "agentOutput": { - "label": "Agent Output", - "format": "text" - }, - "verdicts": { - "label": "Verdicts", - "format": "array" - }, - "metrics": { - "label": "Metrics", - "format": "object" - }, - "efficiency": { - "label": "Efficiency", - "format": "object" - }, - "trajectory": { - "label": "Trajectory", - "format": "object" - }, - "discoverability": { - "label": "Discoverability", - "format": "object" - }, - "error": { - "label": "Error", - "format": "text" - } - } - } - } - } -} diff --git a/actors/runner/.actor/dataset_schema.json b/actors/runner/.actor/dataset_schema.json index 3e5222f..de34666 100644 --- a/actors/runner/.actor/dataset_schema.json +++ b/actors/runner/.actor/dataset_schema.json @@ -6,104 +6,21 @@ "title": "Eval Results", "transformation": { "fields": [ - "scenarioName", "testIndex", - "agent", - "model", "overallVerdict", - "stopReason", - "metrics.totalCostUsd", - "metrics.durationMs", - "metrics.numTurns", - "trajectory.toolCallCount", - "efficiency.cacheHitRate", - "retryAttempts", - "error" - ] - }, - "display": { - "component": "table", - "properties": { - "scenarioName": { - "label": "Scenario", - "format": "text" - }, - "testIndex": { - "label": "#", - "format": "number" - }, - "agent": { - "label": "Agent", - "format": "text" - }, - "model": { - "label": "Model", - "format": "text" - }, - "overallVerdict": { - "label": "Verdict", - "format": "text" - }, - "stopReason": { - "label": "Stop", - "format": "text" - }, - "metrics.totalCostUsd": { - "label": "Cost ($)", - "format": "number" - }, - "metrics.durationMs": { - "label": "Duration (ms)", - "format": "number" - }, - "metrics.numTurns": { - "label": "Turns", - "format": "number" - }, - "trajectory.toolCallCount": { - "label": "Tool Calls", - "format": "number" - }, - "efficiency.cacheHitRate": { - "label": "Cache Hit", - "format": "number" - }, - "retryAttempts": { - "label": "Retries", - "format": "number" - }, - "error": { - "label": "Error", - "format": "text" - } - } - } - }, - "verdicts": { - "title": "Checkpoint Verdicts", - "transformation": { - "fields": [ - "scenarioName", - "testIndex", + "testPrompt", + "agentOutput", "verdicts" - ], - "unwind": ["verdicts"] + ] }, "display": { "component": "table", "properties": { - "scenarioName": { - "label": "Scenario", - "format": "text" - }, - "testIndex": { - "label": "#", - "format": "number" - }, - "verdicts": { - "label": "Verdicts", - "format": "object" - } + "testIndex": { "label": "Test #", "format": "number" }, + "overallVerdict": { "label": "Verdict", "format": "text" }, + "testPrompt": { "label": "Prompt", "format": "text" }, + "agentOutput": { "label": "Agent Output", "format": "text" }, + "verdicts": { "label": "Checks", "format": "array" } } } }