fix(agent): fail fast and name the model on model-not-found errors

A Databricks v2 agent configured with the bare id gpt-6-astra got a 404
(the endpoint is databricks-gpt-6-astra). The harness retried the batch
10 times over ~40 minutes before posting the raw error, and the picker
could not offer the right id because the v2 gateway listing lags v1.

Dead-letter -32002 immediately with a notice that names the model,
supplement v2 discovery with v1 databricks-* endpoints, add a gpt-6
capability rule, and name the rejected model in the desktop copy.

Signed-off-by: Diem Nguyen <diem@squareup.com>

scripts/model-capabilities.json

@@ -259,6 +259,30 @@
       "databricks_v2_wire_route": "openai-responses",
       "normalization_policy": "openai-standard"
     },
+    {
+      "id": "openai-gpt6",
+      "match_kind": "prefix",
+      "match_value": "gpt-6",
+      "match_aliases": [
+        "gpt6"
+      ],
+      "providers": [
+        "openai",
+        "databricks",
+        "databricks_v2"
+      ],
+      "thinking_mode": "none",
+      "supported_efforts": [
+        "low",
+        "medium",
+        "high",
+        "xhigh",
+        "max"
+      ],
+      "default_effort": "medium",
+      "databricks_v2_wire_route": "openai-responses",
+      "normalization_policy": "openai-standard"
+    },
     {
       "id": "openai-gpt5-6",
       "match_kind": "prefix",

scripts/normative-corpus.json

@@ -2035,20 +2035,19 @@
     "id": "uncurated-dbv2-gpt-6-probe",
     "provider": "databricks_v2",
     "raw_model_id": "databricks-gpt-6",
-    "_note": "Probes a non-5 gpt version with no exact record or prefix rule.",
+    "_note": "Probes the bare gpt-6 stem: no exact record, binds to the gpt-6 prefix rule.",
     "expect": {
       "thinking_mode": "none",
       "supported_efforts": [
-        "none",
-        "minimal",
         "low",
         "medium",
         "high",
-        "xhigh"
+        "xhigh",
+        "max"
       ],
       "default_effort": "medium",
-      "databricks_v2_wire_route": "mlflow-chat",
-      "normalization_policy": "openai-clamp-max-to-xhigh",
+      "databricks_v2_wire_route": "openai-responses",
+      "normalization_policy": "openai-standard",
       "registry_label": null
     }
   },