Complete phase two benchmarks, plot previews and static export workflow

2026-09-07 02:54:52 +08:00
parent 95095197df
commit 89df10bc4e
59 changed files with 2535 additions and 83 deletions
@@ -0,0 +1,89 @@
+{
+  "dataset_id": "agent-core-v1",
+  "kind": "agent",
+  "version": "1.0.0",
+  "description": "受限真实 Runtime 工具选择、参数、无需调用和 Markdown 目录基线；不等同于复杂任务验收",
+  "cases": [
+    {
+      "case_id": "arithmetic",
+      "prompt": "必须调用 math.add 计算 17 + 25，并报告结果。",
+      "allowed_tools": [
+        "math.add",
+        "system.echo"
+      ],
+      "expected_tools": [
+        {
+          "name": "math.add",
+          "arguments": {
+            "left": 17,
+            "right": 25
+          }
+        }
+      ],
+      "output_contains": [
+        "42"
+      ],
+      "tags": [
+        "tool-selection",
+        "arguments"
+      ]
+    },
+    {
+      "case_id": "echo",
+      "prompt": "调用 system.echo 原样回显字符串 phase2-check，然后回答原文。",
+      "allowed_tools": [
+        "math.add",
+        "system.echo"
+      ],
+      "expected_tools": [
+        {
+          "name": "system.echo",
+          "arguments": {
+            "text": "phase2-check"
+          }
+        }
+      ],
+      "output_contains": [
+        "phase2-check"
+      ],
+      "tags": [
+        "exact-arguments"
+      ]
+    },
+    {
+      "case_id": "no-tool",
+      "prompt": "不调用任何工具，只回答：验收就绪",
+      "allowed_tools": [
+        "math.add",
+        "system.echo"
+      ],
+      "expected_tools": [],
+      "output_contains": [
+        "验收就绪"
+      ],
+      "tags": [
+        "unnecessary-tools"
+      ]
+    },
+    {
+      "case_id": "markdown-catalog",
+      "prompt": "使用 markdown.catalog 查询支持的 Markdown 语法，指出函数图像围栏的名称。",
+      "allowed_tools": [
+        "markdown.catalog"
+      ],
+      "expected_tools": [
+        {
+          "name": "markdown.catalog",
+          "arguments": {}
+        }
+      ],
+      "output_contains": [
+        "function-plot"
+      ],
+      "tags": [
+        "markdown",
+        "integration"
+      ]
+    }
+  ]
+}