Vercel v5

CHANGELOG.md

@@ -46,6 +46,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 - Exa tools no longer MCP.
+- Adapt everything to vercel v5.
+- Adapt to Response API.
+
 
 ## [v0.11.5] - 6.11.2025
 
@@ -104,6 +107,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Try to enforce using metric tools rather than downloading assets.
 - Rule to avoid overvalidating.
 
+
 ## [v0.10.0] - 2.10.2025
 
 ### Fixed

backend/eval/output/scores.json

@@ -3,244 +3,244 @@
   "metrics_df": [
     {
       "test_name": "cerebellum_morphologies",
-      "Correctness [GEval]": 0.7353869349174808,
+      "Correctness [GEval]": 0.5378027691066317,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "cerebellum_morphologies_descendants",
-      "Correctness [GEval]": 0.7043457159658145,
+      "Correctness [GEval]": 0.7693448910375766,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.5,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "connectivity_metrics",
-      "Correctness [GEval]": 0.8413822094291581,
+      "Correctness [GEval]": 0.8282548737644898,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.5,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "connectivity_metrics_extra_filters",
-      "Correctness [GEval]": 0.8070269281059362,
+      "Correctness [GEval]": 0.8709177678372655,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.5,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "cortex_morphologies",
-      "Correctness [GEval]": 0.4653298006903742,
-      "Tool Correctness": 0.5,
+      "Correctness [GEval]": 0.5362164060624173,
+      "Tool Correctness": 1.0,
       "Argument Correctness": 0.0,
-      "Deterministic Argument Correctness": 0.0,
-      "Overall Argument Correctness": 0.0
+      "Deterministic Argument Correctness": 1.0,
+      "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "get_specific_circuit",
-      "Correctness [GEval]": 0.4548528662574201,
-      "Tool Correctness": 0.0,
+      "Correctness [GEval]": 0.8622402310750299,
+      "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 0.0,
+      "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "hippocampus_morphologies",
-      "Correctness [GEval]": 0.4451658056800826,
+      "Correctness [GEval]": 0.28530009631183456,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.0,
-      "Deterministic Argument Correctness": 0.75,
-      "Overall Argument Correctness": 0.75
+      "Deterministic Argument Correctness": 0.6666666666666666,
+      "Overall Argument Correctness": 0.6666666666666666
     },
     {
       "test_name": "ion_channel",
-      "Correctness [GEval]": 0.7807403647069058,
+      "Correctness [GEval]": 0.7820330992678872,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.5,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "ion_channel_recording",
-      "Correctness [GEval]": 0.8749718614233014,
+      "Correctness [GEval]": 0.5556731982805367,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 0.5,
+      "Deterministic Argument Correctness": 0.625,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "literature_search",
-      "Correctness [GEval]": 0.648942087564872,
+      "Correctness [GEval]": 0.9471472414785973,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "me_model_glossary",
-      "Correctness [GEval]": 0.683306831536382,
-      "Tool Correctness": 1.0,
+      "Correctness [GEval]": 0.5537974270369953,
+      "Tool Correctness": 0.0,
       "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 1.0,
+      "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "morphology_studies",
-      "Correctness [GEval]": 0.4840374574429811,
+      "Correctness [GEval]": 0.8922801826803916,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "neuroscientists_search",
-      "Correctness [GEval]": 0.7001340077257124,
+      "Correctness [GEval]": 0.7275925796421102,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "off_topic_cooking",
-      "Correctness [GEval]": 0.5945247609273225,
+      "Correctness [GEval]": 0.5978033804771575,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "off_topic_programming",
-      "Correctness [GEval]": 0.7695570160957931,
+      "Correctness [GEval]": 0.8565314307651558,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "off_topic_sports",
-      "Correctness [GEval]": 0.8057059705376057,
+      "Correctness [GEval]": 0.7509455475364661,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "off_topic_weather",
-      "Correctness [GEval]": 0.6890006117592387,
+      "Correctness [GEval]": 0.5413464829505792,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "platform_explore",
-      "Correctness [GEval]": 0.2853000957950641,
+      "Correctness [GEval]": 0.27294881512648356,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "platform_news",
-      "Correctness [GEval]": 0.8330807047145509,
+      "Correctness [GEval]": 0.804995298303768,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "platform_ui_simulate",
-      "Correctness [GEval]": 0.5975963651681446,
+      "Correctness [GEval]": 0.34272411774196826,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "platform_viewing",
-      "Correctness [GEval]": 0.6731008652407333,
+      "Correctness [GEval]": 0.72747771401505,
       "Tool Correctness": 1.0,
       "Argument Correctness": 0.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "plotting",
-      "Correctness [GEval]": 0.7366374977736997,
+      "Correctness [GEval]": 0.6127246801610241,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.5,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "read_paper",
-      "Correctness [GEval]": 0.32354476156942,
-      "Tool Correctness": 1.0,
-      "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 1.0,
-      "Overall Argument Correctness": 1.0
+      "Correctness [GEval]": 0.7122372263400929,
+      "Tool Correctness": 0.0,
+      "Argument Correctness": 0.0,
+      "Deterministic Argument Correctness": 0.0,
+      "Overall Argument Correctness": 0.0
     },
     {
       "test_name": "sin_plot",
-      "Correctness [GEval]": 0.43660922801944063,
+      "Correctness [GEval]": 0.7415472928297893,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "software_docs_entitysdk",
-      "Correctness [GEval]": 0.7795970779907103,
+      "Correctness [GEval]": 0.6813881453094685,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 0.0,
+      "Deterministic Argument Correctness": 0.2,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "software_docs_obione",
-      "Correctness [GEval]": 0.6725945299889496,
+      "Correctness [GEval]": 0.8310577292713972,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
-      "Deterministic Argument Correctness": 0.0,
+      "Deterministic Argument Correctness": 0.2,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "species_list",
-      "Correctness [GEval]": 0.6400358146726484,
+      "Correctness [GEval]": 0.6566399827580228,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 1.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "thalamus_id",
-      "Correctness [GEval]": 0.7415867699349027,
+      "Correctness [GEval]": 0.659614380970777,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.5,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "warning_test",
-      "Correctness [GEval]": 0.618138951957894,
+      "Correctness [GEval]": 0.7849753604657479,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     },
     {
       "test_name": "web_search",
-      "Correctness [GEval]": 0.4164325021025331,
+      "Correctness [GEval]": 0.7085964582401003,
       "Tool Correctness": 1.0,
       "Argument Correctness": 1.0,
       "Deterministic Argument Correctness": 0.0,
       "Overall Argument Correctness": 1.0
     }
   ],
-  "created_at": "2025-11-28 16:33:30.267246"
-}
+  "created_at": "2025-12-09 11:28:17.260619"
+}