evalbuff: add carve-based eval pipeline (delete & rebuild)

New approach to evals that carves features out of the current codebase
and has agents rebuild them, instead of replaying git commits. Uses
OpenAI SDK (gpt-5.4) to identify and surgically remove features, then
runs agents in parallel to rebuild from a natural prompt, judges against
original code, and iterates on docs.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Author: jahooma

bun.lock

@@ -18,6 +18,7 @@
     "@codebuff/common": "workspace:*",
     "@codebuff/sdk": "workspace:*",
     "ai": "^5.0.0",
+    "openai": "^6.33.0",
     "zod": "^4.2.1"
   }
 }