evalbuff: carve-based eval pipeline (delete & rebuild) (#487)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Author: jahooma

AGENTS.md

@@ -43,3 +43,4 @@ Make an efficient learning agent that can do anything.
 - [`docs/agents-and-tools.md`](docs/agents-and-tools.md) — Agent system, shell shims, tool definitions
 - [`docs/patterns/handle-steps-generators.md`](docs/patterns/handle-steps-generators.md) — handleSteps generator patterns and spawn_agents tool calls
 - [docs/evalbuff/interpreting-task-prompts.md](docs/evalbuff/interpreting-task-prompts.md)
+- [docs/patterns/discover-before-implement.md](docs/patterns/discover-before-implement.md)

bun.lock

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