feat(databricks): update model capability flags from live API probes

- Correct attachment flags: gpt-oss-120b, gpt-oss-20b, qwen3-next-80b set to false
  (gateway returns "Image input is not supported for this endpoint")
- Add pdf to modalities.input for all Gemini models and Codex models
  (confirmed via inlineData / Responses API input_file probes)
- Set temperature=false for all gpt-5* models (policy rule):
  base variants return HTTP 400 "Only the default (1) value is supported";
  all gpt-5* unified to false for catalog consistency
- Fix gpt-5-nano tool_call: true (false negative - now uses tool_choice:"required")
- Add reasoning=true for gpt-5-nano (reasoning_tokens confirmed in usage)
- Add reasoning=true for gemma-3-12b (<think> blocks confirmed via system prompt)
- Add probe script: packages/core/script/probe-databricks-capabilities.ts
  Tests tool-use, reasoning, image, PDF, and temperature across all 4 API surfaces
  (mlflow/v1 chat, Anthropic, Gemini, OpenAI Responses). Read-only diagnostic tool.

Author: prasadkona

package.json

@@ -22,7 +22,8 @@
     "vercel:generate": "bun ./packages/core/script/generate-vercel.ts",
     "wandb:generate": "bun ./packages/core/script/generate-wandb.ts",
     "databricks:list-gateway": "bun ./packages/core/script/list-databricks-ai-gateway.ts",
-    "databricks:test-inference": "bun ./packages/core/script/test-databricks.ts"
+    "databricks:test-inference": "bun ./packages/core/script/test-databricks.ts",
+    "databricks:probe-capabilities": "bun ./packages/core/script/probe-databricks-capabilities.ts"
   },
   "dependencies": {
     "@cloudflare/workers-types": "^4.20250801.0",