fix: remove unused grader targets from offline-grader-benchmark

These azure/openrouter grader definitions were causing warnings
and are no longer needed — fixture_replay now uses root grader.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: christso

examples/showcase/offline-grader-benchmark/.agentv/targets.yaml

@@ -7,23 +7,3 @@ targets:
     healthcheck:
       command: bun run ./scripts/replay-fixture-output.ts --healthcheck
       cwd: ..
-
-  # Illustrative low-cost grader targets. Swap these to the low-cost models you already use.
-  - name: grader_gpt_5_mini
-    provider: azure
-    endpoint: ${{ AZURE_OPENAI_ENDPOINT }}
-    api_key: ${{ AZURE_OPENAI_API_KEY }}
-    version: ${{ AZURE_OPENAI_API_VERSION }}
-    model: ${{ AZURE_DEPLOYMENT_NAME }}
-
-  - name: grader_claude_haiku
-    provider: openrouter
-    api_key: ${{ OPENROUTER_API_KEY }}
-    model: anthropic/claude-haiku-4.5
-    system_prompt: "Return concise structured grading output only."
-
-  - name: grader_gemini_flash
-    provider: openrouter
-    api_key: ${{ OPENROUTER_API_KEY }}
-    model: google/gemini-3-flash-preview
-    system_prompt: "Return concise structured grading output only."