minovative-mind-cli 2.11.4 → 2.12.0

package/oclif.manifest.json

@@ -24,6 +24,142 @@
         "chat.js"
       ]
     },
+    "eval": {
+      "aliases": [],
+      "args": {},
+      "description": "Execute automated evaluation on SWE-bench Lite benchmark instances",
+      "examples": [
+        "<%= config.bin %> <%= command.id %> -i instances.json -o predictions.jsonl",
+        "<%= config.bin %> <%= command.id %> --instances ./test_instances.jsonl --output ./predictions.jsonl --report ./evaluation_report.json",
+        "<%= config.bin %> <%= command.id %> --instances test_instances.jsonl --repo astropy/astropy --limit 5",
+        "<%= config.bin %> <%= command.id %> --instances test_instances.jsonl --instance-id astropy__astropy-12907",
+        "<%= config.bin %> <%= command.id %> --instances test_instances.jsonl --dry-run"
+      ],
+      "flags": {
+        "instances": {
+          "char": "i",
+          "description": "Path to input instances file (JSON or JSONL format)",
+          "name": "instances",
+          "required": true,
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "output": {
+          "char": "o",
+          "description": "Path to write generated predictions JSONL file",
+          "name": "output",
+          "default": "predictions.jsonl",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "report": {
+          "char": "r",
+          "description": "Path to export comprehensive evaluation report JSON",
+          "name": "report",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "model": {
+          "char": "m",
+          "description": "Model name tag for prediction metadata",
+          "name": "model",
+          "default": "minovative-mind-agent",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "maxTurns": {
+          "description": "Maximum agent execution turns per benchmark instance",
+          "name": "maxTurns",
+          "default": 30,
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "timeout": {
+          "description": "Timeout in milliseconds per instance (default: 600000ms = 10min)",
+          "name": "timeout",
+          "default": 600000,
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "repo": {
+          "description": "Filter instances by repository name (e.g. astropy/astropy)",
+          "name": "repo",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "instanceId": {
+          "description": "Filter by specific instance ID (e.g. astropy__astropy-12907)",
+          "name": "instanceId",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "limit": {
+          "description": "Limit the number of instances to evaluate",
+          "name": "limit",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "workspaceDir": {
+          "char": "w",
+          "description": "Base workspace directory where repo checkouts reside",
+          "name": "workspaceDir",
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "autoClone": {
+          "description": "Automatically clone repository if not found locally in workspace directory",
+          "name": "autoClone",
+          "allowNo": false,
+          "type": "boolean"
+        },
+        "dryRun": {
+          "description": "Validate instances and workspace setup without invoking the agent loop",
+          "name": "dryRun",
+          "allowNo": false,
+          "type": "boolean"
+        },
+        "concurrency": {
+          "char": "c",
+          "description": "Number of instances to evaluate concurrently (default: 1)",
+          "name": "concurrency",
+          "default": 1,
+          "hasDynamicHelp": false,
+          "multiple": false,
+          "type": "option"
+        },
+        "verbose": {
+          "char": "v",
+          "description": "Show detailed per-turn logs during evaluation",
+          "name": "verbose",
+          "allowNo": false,
+          "type": "boolean"
+        }
+      },
+      "hasDynamicHelp": false,
+      "hiddenAliases": [],
+      "id": "eval",
+      "pluginAlias": "minovative-mind-cli",
+      "pluginName": "minovative-mind-cli",
+      "pluginType": "core",
+      "strict": true,
+      "enableJsonFlag": false,
+      "isESM": true,
+      "relativePath": [
+        "dist",
+        "commands",
+        "eval.js"
+      ]
+    },
     "login": {
       "aliases": [],
       "args": {},
@@ -65,5 +201,5 @@
       ]
     }
   },
-  "version": "2.11.4"
+  "version": "2.12.0"
 }

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "minovative-mind-cli",
   "description": "An automated AI agent powered by Vertex AI that helps you write software",
-  "version": "2.11.4",
+  "version": "2.12.0",
   "author": "Daniel Ward",
   "bin": {
     "minovative-mind-cli": "bin/run.js"