fix: spell swe-bench-pro's models the way the gateway matches them

The agents strip only the `openai/` prefix before calling the gateway
(`removeprefix("openai/")`), and the gateway matches the allow-list exactly
(`model not in scope.allowed_models` -> 403 model_denied). So `model:
openai/gpt-4o` puts `gpt-4o` on the wire, and an allow-list carrying the
prefixed spelling never matches. Listing both spellings papered over that
and then fails the config invariant that the evaluation scope allow exactly
the target model.

Drop the prefix on both sides, and template the producer list the way every
other benchmark does so `--model` / `--param optimizer_model` keeps working
without a config edit.

This config still cannot be swept by tests/test_v05_benchmark_configs.py:
its partitions are deliberately empty pending real task ids, so it fails to
load. It should join BENCHMARKS there once the partitions and the task
source digest are pinned.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

Author: shehabyasser-scale

harness-engineering-bench/swe-bench-pro/baseline/build.yaml

@@ -49,7 +49,7 @@ score_baseline: true
 rescore_top_k: 3
 rescore_attempts: 1
 
-model: openai/gpt-4o
+model: gpt-4o
 environment_name: ${inner_env:-modal}
 # inner eval sandboxes share a dedicated Modal app instead of the __harbor__ default
 extra_harbor_args: ["--ek", "app_name=harness-engineering-bench", "--ek", "sandbox_idle_timeout_secs=3600"]
@@ -90,10 +90,10 @@ inference_gateway:
   upstream_base_url_env: OPENAI_BASE_URL
   producer:
     # Both prefixed and bare forms: the gateway model match is prefix-sensitive.
-    allowed_models: ["gpt-5.3-codex", "openai/gpt-5.3-codex"]
+    allowed_models: ["${optimizer_model:-gpt-5.3-codex}"]
     max_concurrency: 8
   evaluation:
-    allowed_models: ["gpt-4o", "openai/gpt-4o"]
+    allowed_models: [gpt-4o]
     max_requests: 15000
     max_tokens: 100000000
     max_concurrency: 64